diff --git "a/AntBullet.ipynb" "b/AntBullet.ipynb" new file mode 100644--- /dev/null +++ "b/AntBullet.ipynb" @@ -0,0 +1,8260 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "language_info": { + "name": "python" + }, + "accelerator": "GPU", + "gpuClass": "standard", + "widgets": { + "application/vnd.jupyter.widget-state+json": { + "156c5533e16243a7bda1e84f80f5114e": { + "model_module": "@jupyter-widgets/controls", + "model_name": "VBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "VBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "VBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_a00a11e622d44f97a332fd474ce466cd", + "IPY_MODEL_2b6fb2c35de748c08c963729d8e420ce", + "IPY_MODEL_6b0b5d0652954f6788de81be2aed4a91", + "IPY_MODEL_c2e98a3f69eb4567a59bfc3b2dc75d09", + "IPY_MODEL_4f9c9bf144f24505ae9d7f37a2e08469" + ], + "layout": "IPY_MODEL_c0c745264866433d9a23bace3f6942ca" + } + }, + "a00a11e622d44f97a332fd474ce466cd": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_6b327d9a12d04092a0c35e22641749f6", + "placeholder": "​", + "style": "IPY_MODEL_605f13ce1adb4ec19fb28be89862662f", + "value": "

Copy a token from your Hugging Face\ntokens page and paste it below.
Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file.
" + } + }, + "2b6fb2c35de748c08c963729d8e420ce": { + "model_module": "@jupyter-widgets/controls", + "model_name": "PasswordModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "PasswordModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "PasswordView", + "continuous_update": true, + "description": "Token:", + "description_tooltip": null, + "disabled": false, + "layout": "IPY_MODEL_3458c418bf9e4790b3bb58eb411afa84", + "placeholder": "​", + "style": "IPY_MODEL_ec672f86dbe54f779c83a55e124d3529", + "value": "" + } + }, + "6b0b5d0652954f6788de81be2aed4a91": { + "model_module": "@jupyter-widgets/controls", + "model_name": "CheckboxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "CheckboxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "CheckboxView", + "description": "Add token as git credential?", + "description_tooltip": null, + "disabled": false, + "indent": true, + "layout": "IPY_MODEL_487a8dfceb5d4c0c961920dd87f6c3dc", + "style": "IPY_MODEL_6006287334cb4569b285b532feeb1bac", + "value": true + } + }, + "c2e98a3f69eb4567a59bfc3b2dc75d09": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ButtonModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ButtonModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ButtonView", + "button_style": "", + "description": "Login", + "disabled": false, + "icon": "", + "layout": "IPY_MODEL_3cb0781eaf4d40f192bd3c0e9b0e7754", + "style": "IPY_MODEL_e89bd84972124556842d0b8b88c53c82", + "tooltip": "" + } + }, + "4f9c9bf144f24505ae9d7f37a2e08469": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_9044266c2ffd42caa0fbca6a6c0cfe1c", + "placeholder": "​", + "style": "IPY_MODEL_59d495c7bac64601b8290f2b91a5f95a", + "value": "\nPro Tip: If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks. " + } + }, + "c0c745264866433d9a23bace3f6942ca": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": "center", + "align_self": null, + "border": null, + "bottom": null, + "display": "flex", + "flex": null, + "flex_flow": "column", + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": "50%" + } + }, + "6b327d9a12d04092a0c35e22641749f6": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "605f13ce1adb4ec19fb28be89862662f": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "3458c418bf9e4790b3bb58eb411afa84": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "ec672f86dbe54f779c83a55e124d3529": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "487a8dfceb5d4c0c961920dd87f6c3dc": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "6006287334cb4569b285b532feeb1bac": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "3cb0781eaf4d40f192bd3c0e9b0e7754": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "e89bd84972124556842d0b8b88c53c82": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ButtonStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ButtonStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "button_color": null, + "font_weight": "" + } + }, + "9044266c2ffd42caa0fbca6a6c0cfe1c": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "59d495c7bac64601b8290f2b91a5f95a": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "3f0e1549af384b5eaaf8d0e0947ffa63": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_2469c6a556f646ce948ebaf91538b6f9", + "IPY_MODEL_edd595ea0bcb4405babbd89ce001b713", + "IPY_MODEL_32befdf329704957a799f02d4b567809" + ], + "layout": "IPY_MODEL_20705240642b484e9d3600c1e1b59fd4" + } + }, + "2469c6a556f646ce948ebaf91538b6f9": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_4df6f9ecc994445e869d4f166b993275", + "placeholder": "​", + "style": "IPY_MODEL_630be75737424612b4548699931d42a1", + "value": "policy.optimizer.pth: 100%" + } + }, + "edd595ea0bcb4405babbd89ce001b713": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_25ed9665e62541ccb2cb7c54abc9893a", + "max": 56190, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_f2bb94fa4b1f45a4b6a3b2733f286ee0", + "value": 56190 + } + }, + "32befdf329704957a799f02d4b567809": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_e9ee36a505784dffb619f0a371e1f30a", + "placeholder": "​", + "style": "IPY_MODEL_dd9c3c14cdc047608c52232da0922fbf", + "value": " 56.2k/56.2k [00:01<00:00, 19.8kB/s]" + } + }, + "20705240642b484e9d3600c1e1b59fd4": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "4df6f9ecc994445e869d4f166b993275": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "630be75737424612b4548699931d42a1": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "25ed9665e62541ccb2cb7c54abc9893a": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "f2bb94fa4b1f45a4b6a3b2733f286ee0": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "e9ee36a505784dffb619f0a371e1f30a": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "dd9c3c14cdc047608c52232da0922fbf": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "dbdf621979244bc884d5978a717964ec": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_2a0d9775e20848af8b1dd2d816c29c83", + "IPY_MODEL_95aa8c1e9a16422d80c39b58a6f41be2", + "IPY_MODEL_b517ca6b785e4f3da25f0ac3479baf27" + ], + "layout": "IPY_MODEL_13e80013881248a596b2f5e66ded6b78" + } + }, + "2a0d9775e20848af8b1dd2d816c29c83": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_91956ea4266f4f569b213216f4152b4a", + "placeholder": "​", + "style": "IPY_MODEL_3c32343528234482b6074b484eabf35b", + "value": "policy.pth: 100%" + } + }, + "95aa8c1e9a16422d80c39b58a6f41be2": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_ff3776982a9f447d9358034b6173810b", + "max": 56958, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_9beb866c18d642c09026f72b7162f705", + "value": 56958 + } + }, + "b517ca6b785e4f3da25f0ac3479baf27": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_dc4d21ed062441189ade718a1637ce15", + "placeholder": "​", + "style": "IPY_MODEL_d5dc4b70fddf44b69380a621dd07776f", + "value": " 57.0k/57.0k [00:01<00:00, 21.3kB/s]" + } + }, + "13e80013881248a596b2f5e66ded6b78": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "91956ea4266f4f569b213216f4152b4a": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "3c32343528234482b6074b484eabf35b": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "ff3776982a9f447d9358034b6173810b": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "9beb866c18d642c09026f72b7162f705": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "dc4d21ed062441189ade718a1637ce15": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "d5dc4b70fddf44b69380a621dd07776f": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "0b1acf65b5d54bb2b7139d3ec608b1dc": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_8f49d8154ba141439baff19887525f58", + "IPY_MODEL_adc728f4a9a34defbca502e64ecbd6bd", + "IPY_MODEL_c8ac80f0d8a540f2a0f10f2c1de7120e" + ], + "layout": "IPY_MODEL_ab9d88cffbe44792b4f33f48a35ea207" + } + }, + "8f49d8154ba141439baff19887525f58": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_0da068b4a75d4eba823d4b1524d383b9", + "placeholder": "​", + "style": "IPY_MODEL_db4ed7c243ff44779319129275047d19", + "value": "Upload 5 LFS files: 100%" + } + }, + "adc728f4a9a34defbca502e64ecbd6bd": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_a77ed51197ef4c8698000cd6486031ec", + "max": 5, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_72f5f757970c42e9acfa251a43c78d29", + "value": 5 + } + }, + "c8ac80f0d8a540f2a0f10f2c1de7120e": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_b723acd11a59442a935c4bf48bd08cc2", + "placeholder": "​", + "style": "IPY_MODEL_ee40cee766c140f997d5d2e0df1791de", + "value": " 5/5 [00:01<00:00, 3.93it/s]" + } + }, + "ab9d88cffbe44792b4f33f48a35ea207": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "0da068b4a75d4eba823d4b1524d383b9": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "db4ed7c243ff44779319129275047d19": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "a77ed51197ef4c8698000cd6486031ec": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "72f5f757970c42e9acfa251a43c78d29": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "b723acd11a59442a935c4bf48bd08cc2": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "ee40cee766c140f997d5d2e0df1791de": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "4c6ab63c95874d1e807d4b9d13ecbe71": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_46b2a515f62743f38e36bd34f3c4c25d", + "IPY_MODEL_5027a441cf3f462baecc84aa26d9aaa9", + "IPY_MODEL_65af073891b745749747b04a1109e3a7" + ], + "layout": "IPY_MODEL_5101355a7838441b86f3afe843d479b3" + } + }, + "46b2a515f62743f38e36bd34f3c4c25d": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_3a13164d7885436a8cc75f174ad1a800", + "placeholder": "​", + "style": "IPY_MODEL_31f4fc6dc22a47829f44408249d4d106", + "value": "a2c-AntBulletEnv-v0.zip: 100%" + } + }, + "5027a441cf3f462baecc84aa26d9aaa9": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_84df193e14c04a2286852ee3994de7ef", + "max": 129266, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_c7fcb03dc92e4e5b85d29e57fc36b6c7", + "value": 129266 + } + }, + "65af073891b745749747b04a1109e3a7": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_b9bd6fdb316b46d1974c63deb3d592f3", + "placeholder": "​", + "style": "IPY_MODEL_ff3f469eff2148c192e618cfdf5af008", + "value": " 129k/129k [00:01<00:00, 20.5kB/s]" + } + }, + "5101355a7838441b86f3afe843d479b3": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "3a13164d7885436a8cc75f174ad1a800": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "31f4fc6dc22a47829f44408249d4d106": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "84df193e14c04a2286852ee3994de7ef": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "c7fcb03dc92e4e5b85d29e57fc36b6c7": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "b9bd6fdb316b46d1974c63deb3d592f3": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "ff3f469eff2148c192e618cfdf5af008": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "f228987c7fc64d30ba7c2f9d0ae971ab": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_052da86de60c4d42b9ff3443ae2167fd", + "IPY_MODEL_8c5c76524e354e2da1155e0d2d16f14e", + "IPY_MODEL_85a94779b184457d88483a0c653b6865" + ], + "layout": "IPY_MODEL_ba7239084fee470db29a8410cba7a859" + } + }, + "052da86de60c4d42b9ff3443ae2167fd": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_273e4cb1ebc24a438700a8acb626453b", + "placeholder": "​", + "style": "IPY_MODEL_e8fb69888ba3487c9fa62449cbc665e8", + "value": "pytorch_variables.pth: 100%" + } + }, + "8c5c76524e354e2da1155e0d2d16f14e": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_0010ce3516404b229534792c804a2108", + "max": 431, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_ec031f4349804865bf1a43c6a439f3ce", + "value": 431 + } + }, + "85a94779b184457d88483a0c653b6865": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_f1ea5d94c4fd4da7b9dbddf4baf51858", + "placeholder": "​", + "style": "IPY_MODEL_0342b70c06d54475aec9a096678976e8", + "value": " 431/431 [00:01<00:00, 1.18kB/s]" + } + }, + "ba7239084fee470db29a8410cba7a859": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "273e4cb1ebc24a438700a8acb626453b": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "e8fb69888ba3487c9fa62449cbc665e8": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "0010ce3516404b229534792c804a2108": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "ec031f4349804865bf1a43c6a439f3ce": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "f1ea5d94c4fd4da7b9dbddf4baf51858": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "0342b70c06d54475aec9a096678976e8": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "70550b80f84f4c2c8a78507f4d4b7d7d": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_68b0a8b98bc64437b21321bc81ecabda", + "IPY_MODEL_76792056dc8e41b8b429dbaedcc8b959", + "IPY_MODEL_21dfca4be5ec4153a0092408c4cd8008" + ], + "layout": "IPY_MODEL_ae165b0638e44c7c8e4ed2883ad54780" + } + }, + "68b0a8b98bc64437b21321bc81ecabda": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_457a90c53184449cb84aac8566a0c5ee", + "placeholder": "​", + "style": "IPY_MODEL_f65d8a0e537e42aeb05ad14d01736838", + "value": "vec_normalize.pkl: 100%" + } + }, + "76792056dc8e41b8b429dbaedcc8b959": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_893f301fae2d407b88fa5222b33960e8", + "max": 2123, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_e890edf0b0db4e29b6bae6e255e7ea60", + "value": 2123 + } + }, + "21dfca4be5ec4153a0092408c4cd8008": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_a3f2601e95cc46fba98c2b831a90c590", + "placeholder": "​", + "style": "IPY_MODEL_cb1b15ddb2aa4cc7b4816fbff9c264ec", + "value": " 2.12k/2.12k [00:00<00:00, 5.56kB/s]" + } + }, + "ae165b0638e44c7c8e4ed2883ad54780": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "457a90c53184449cb84aac8566a0c5ee": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "f65d8a0e537e42aeb05ad14d01736838": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "893f301fae2d407b88fa5222b33960e8": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "e890edf0b0db4e29b6bae6e255e7ea60": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "a3f2601e95cc46fba98c2b831a90c590": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "cb1b15ddb2aa4cc7b4816fbff9c264ec": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + } + } + } + }, + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "id": "4JySv-QmLKk3" + }, + "outputs": [], + "source": [ + "%%capture\n", + "!apt install python-opengl\n", + "!apt install ffmpeg\n", + "!apt install xvfb\n", + "!pip3 install pyvirtualdisplay" + ] + }, + { + "cell_type": "code", + "source": [ + "# Virtual display\n", + "from pyvirtualdisplay import Display\n", + "\n", + "virtual_display = Display(visible=0, size=(1400, 900))\n", + "virtual_display.start()" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "BJStvsI2LZPn", + "outputId": "c4533443-5f6c-4782-b640-82bb5dbf46af" + }, + "execution_count": 2, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "" + ] + }, + "metadata": {}, + "execution_count": 2 + } + ] + }, + { + "cell_type": "code", + "source": [ + "# Install the specific setuptools version required to install the dependencies\n", + "!pip install setuptools==65.5.0" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "H3Kw1GLcNmLr", + "outputId": "f2a02585-d9df-4ef5-d650-25e351dfd5e0" + }, + "execution_count": 3, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", + "Collecting setuptools==65.5.0\n", + " Downloading setuptools-65.5.0-py3-none-any.whl (1.2 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m27.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hInstalling collected packages: setuptools\n", + " Attempting uninstall: setuptools\n", + " Found existing installation: setuptools 67.6.0\n", + " Uninstalling setuptools-67.6.0:\n", + " Successfully uninstalled setuptools-67.6.0\n", + "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n", + "ipython 7.9.0 requires jedi>=0.10, which is not installed.\n", + "cvxpy 1.3.1 requires setuptools>65.5.1, but you have setuptools 65.5.0 which is incompatible.\u001b[0m\u001b[31m\n", + "\u001b[0mSuccessfully installed setuptools-65.5.0\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "!pip install -r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "kzMsxtsvLbe1", + "outputId": "23da9ca2-7ccf-4be4-8ad6-4af99a6db5e3" + }, + "execution_count": 4, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", + "Collecting stable-baselines3[extra]\n", + " Downloading stable_baselines3-1.7.0-py3-none-any.whl (171 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m171.8/171.8 KB\u001b[0m \u001b[31m11.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting huggingface_sb3\n", + " Downloading huggingface_sb3-2.2.4-py3-none-any.whl (9.4 kB)\n", + "Collecting panda_gym==2.0.0\n", + " Downloading panda_gym-2.0.0-py3-none-any.whl (26 kB)\n", + "Collecting pyglet==1.5.1\n", + " Downloading pyglet-1.5.1-py2.py3-none-any.whl (1.0 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.0/1.0 MB\u001b[0m \u001b[31m60.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: scipy in /usr/local/lib/python3.9/dist-packages (from panda_gym==2.0.0->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 3)) (1.10.1)\n", + "Collecting pybullet\n", + " Downloading pybullet-3.2.5-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.whl (91.7 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m91.7/91.7 MB\u001b[0m \u001b[31m9.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: numpy in /usr/local/lib/python3.9/dist-packages (from panda_gym==2.0.0->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 3)) (1.22.4)\n", + "Requirement already satisfied: gym in /usr/local/lib/python3.9/dist-packages (from panda_gym==2.0.0->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 3)) (0.25.2)\n", + "Requirement already satisfied: pandas in /usr/local/lib/python3.9/dist-packages (from stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (1.4.4)\n", + "Requirement already satisfied: cloudpickle in /usr/local/lib/python3.9/dist-packages (from stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (2.2.1)\n", + "Requirement already satisfied: matplotlib in /usr/local/lib/python3.9/dist-packages (from stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (3.7.1)\n", + "Collecting importlib-metadata~=4.13\n", + " Downloading importlib_metadata-4.13.0-py3-none-any.whl (23 kB)\n", + "Requirement already satisfied: torch>=1.11 in /usr/local/lib/python3.9/dist-packages (from stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (1.13.1+cu116)\n", + "Collecting gym\n", + " Downloading gym-0.21.0.tar.gz (1.5 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.5/1.5 MB\u001b[0m \u001b[31m70.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + "Requirement already satisfied: pillow in /usr/local/lib/python3.9/dist-packages (from stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (8.4.0)\n", + "Requirement already satisfied: opencv-python in /usr/local/lib/python3.9/dist-packages (from stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (4.7.0.72)\n", + "Collecting ale-py==0.7.4\n", + " Downloading ale_py-0.7.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.6 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m85.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting autorom[accept-rom-license]~=0.4.2\n", + " Downloading AutoROM-0.4.2-py3-none-any.whl (16 kB)\n", + "Requirement already satisfied: tqdm in /usr/local/lib/python3.9/dist-packages (from stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (4.65.0)\n", + "Requirement already satisfied: tensorboard>=2.9.1 in /usr/local/lib/python3.9/dist-packages (from stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (2.11.2)\n", + "Requirement already satisfied: rich in /usr/local/lib/python3.9/dist-packages (from stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (13.3.2)\n", + "Requirement already satisfied: psutil in /usr/local/lib/python3.9/dist-packages (from stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (5.9.4)\n", + "Requirement already satisfied: importlib-resources in /usr/local/lib/python3.9/dist-packages (from ale-py==0.7.4->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (5.12.0)\n", + "Requirement already satisfied: wasabi in /usr/local/lib/python3.9/dist-packages (from huggingface_sb3->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 2)) (1.1.1)\n", + "Collecting huggingface-hub~=0.8\n", + " Downloading huggingface_hub-0.13.3-py3-none-any.whl (199 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m199.8/199.8 KB\u001b[0m \u001b[31m29.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: pyyaml~=6.0 in /usr/local/lib/python3.9/dist-packages (from huggingface_sb3->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 2)) (6.0)\n", + "Requirement already satisfied: click in /usr/local/lib/python3.9/dist-packages (from autorom[accept-rom-license]~=0.4.2->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (8.1.3)\n", + "Requirement already satisfied: requests in /usr/local/lib/python3.9/dist-packages (from autorom[accept-rom-license]~=0.4.2->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (2.27.1)\n", + "Collecting AutoROM.accept-rom-license\n", + " Downloading AutoROM.accept-rom-license-0.6.0.tar.gz (434 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m434.7/434.7 KB\u001b[0m \u001b[31m50.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25h Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n", + " Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n", + " Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", + "Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.9/dist-packages (from huggingface-hub~=0.8->huggingface_sb3->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 2)) (23.0)\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.9/dist-packages (from huggingface-hub~=0.8->huggingface_sb3->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 2)) (3.10.2)\n", + "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.9/dist-packages (from huggingface-hub~=0.8->huggingface_sb3->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 2)) (4.5.0)\n", + "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.9/dist-packages (from importlib-metadata~=4.13->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (3.15.0)\n", + "Requirement already satisfied: google-auth-oauthlib<0.5,>=0.4.1 in /usr/local/lib/python3.9/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (0.4.6)\n", + "Requirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.9/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (65.5.0)\n", + "Requirement already satisfied: wheel>=0.26 in /usr/local/lib/python3.9/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (0.40.0)\n", + "Requirement already satisfied: tensorboard-plugin-wit>=1.6.0 in /usr/local/lib/python3.9/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (1.8.1)\n", + "Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.9/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (3.4.3)\n", + "Requirement already satisfied: grpcio>=1.24.3 in /usr/local/lib/python3.9/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (1.51.3)\n", + "Requirement already satisfied: absl-py>=0.4 in /usr/local/lib/python3.9/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (1.4.0)\n", + "Requirement already satisfied: werkzeug>=1.0.1 in /usr/local/lib/python3.9/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (2.2.3)\n", + "Requirement already satisfied: google-auth<3,>=1.6.3 in /usr/local/lib/python3.9/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (2.16.2)\n", + "Requirement already satisfied: protobuf<4,>=3.9.2 in /usr/local/lib/python3.9/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (3.19.6)\n", + "Requirement already satisfied: tensorboard-data-server<0.7.0,>=0.6.0 in /usr/local/lib/python3.9/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (0.6.1)\n", + "Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.9/dist-packages (from matplotlib->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (2.8.2)\n", + "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.9/dist-packages (from matplotlib->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (1.4.4)\n", + "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.9/dist-packages (from matplotlib->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (3.0.9)\n", + "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.9/dist-packages (from matplotlib->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (1.0.7)\n", + "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.9/dist-packages (from matplotlib->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (4.39.2)\n", + "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.9/dist-packages (from matplotlib->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (0.11.0)\n", + "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.9/dist-packages (from pandas->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (2022.7.1)\n", + "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.9/dist-packages (from rich->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (2.14.0)\n", + "Requirement already satisfied: markdown-it-py<3.0.0,>=2.2.0 in /usr/local/lib/python3.9/dist-packages (from rich->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (2.2.0)\n", + "Requirement already satisfied: six>=1.9.0 in /usr/local/lib/python3.9/dist-packages (from google-auth<3,>=1.6.3->tensorboard>=2.9.1->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (1.16.0)\n", + "Requirement already satisfied: rsa<5,>=3.1.4 in /usr/local/lib/python3.9/dist-packages (from google-auth<3,>=1.6.3->tensorboard>=2.9.1->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (4.9)\n", + "Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.9/dist-packages (from google-auth<3,>=1.6.3->tensorboard>=2.9.1->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (0.2.8)\n", + "Requirement already satisfied: cachetools<6.0,>=2.0.0 in /usr/local/lib/python3.9/dist-packages (from google-auth<3,>=1.6.3->tensorboard>=2.9.1->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (5.3.0)\n", + "Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.9/dist-packages (from google-auth-oauthlib<0.5,>=0.4.1->tensorboard>=2.9.1->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (1.3.1)\n", + "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.9/dist-packages (from markdown-it-py<3.0.0,>=2.2.0->rich->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (0.1.2)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/dist-packages (from requests->autorom[accept-rom-license]~=0.4.2->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (2022.12.7)\n", + "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests->autorom[accept-rom-license]~=0.4.2->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (1.26.15)\n", + "Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.9/dist-packages (from requests->autorom[accept-rom-license]~=0.4.2->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (2.0.12)\n", + "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests->autorom[accept-rom-license]~=0.4.2->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (3.4)\n", + "Requirement already satisfied: MarkupSafe>=2.1.1 in /usr/local/lib/python3.9/dist-packages (from werkzeug>=1.0.1->tensorboard>=2.9.1->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (2.1.2)\n", + "Collecting libtorrent\n", + " Downloading libtorrent-2.0.7-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (8.6 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.6/8.6 MB\u001b[0m \u001b[31m69.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: pyasn1<0.5.0,>=0.4.6 in /usr/local/lib/python3.9/dist-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard>=2.9.1->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (0.4.8)\n", + "Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.9/dist-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tensorboard>=2.9.1->stable-baselines3[extra]->-r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt (line 1)) (3.2.2)\n", + "Building wheels for collected packages: gym, AutoROM.accept-rom-license\n", + " \u001b[1;31merror\u001b[0m: \u001b[1msubprocess-exited-with-error\u001b[0m\n", + " \n", + " \u001b[31m×\u001b[0m \u001b[32mpython setup.py bdist_wheel\u001b[0m did not run successfully.\n", + " \u001b[31m│\u001b[0m exit code: \u001b[1;36m1\u001b[0m\n", + " \u001b[31m╰─>\u001b[0m See above for output.\n", + " \n", + " \u001b[1;35mnote\u001b[0m: This error originates from a subprocess, and is likely not a problem with pip.\n", + " Building wheel for gym (setup.py) ... \u001b[?25lerror\n", + "\u001b[31m ERROR: Failed building wheel for gym\u001b[0m\u001b[31m\n", + "\u001b[0m\u001b[?25h Running setup.py clean for gym\n", + " Building wheel for AutoROM.accept-rom-license (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for AutoROM.accept-rom-license: filename=AutoROM.accept_rom_license-0.6.0-py3-none-any.whl size=446686 sha256=df944842c58e6336377dd9d6bb6bb5ea16a04c20626162a3f2d986530f123ef4\n", + " Stored in directory: /root/.cache/pip/wheels/7d/17/c9/c31922a6aaf4ec7ec90eeee5dbc40ffbaafeda64b30a208b72\n", + "Successfully built AutoROM.accept-rom-license\n", + "Failed to build gym\n", + "Installing collected packages: pyglet, pybullet, libtorrent, importlib-metadata, gym, panda_gym, huggingface-hub, AutoROM.accept-rom-license, autorom, ale-py, stable-baselines3, huggingface_sb3\n", + " Attempting uninstall: importlib-metadata\n", + " Found existing installation: importlib-metadata 6.1.0\n", + " Uninstalling importlib-metadata-6.1.0:\n", + " Successfully uninstalled importlib-metadata-6.1.0\n", + " Attempting uninstall: gym\n", + " Found existing installation: gym 0.25.2\n", + " Uninstalling gym-0.25.2:\n", + " Successfully uninstalled gym-0.25.2\n", + " Running setup.py install for gym ... \u001b[?25l\u001b[?25hdone\n", + "\u001b[33m DEPRECATION: gym was installed using the legacy 'setup.py install' method, because a wheel could not be built for it. A possible replacement is to fix the wheel build issue reported above. Discussion can be found at https://github.com/pypa/pip/issues/8368\u001b[0m\u001b[33m\n", + "\u001b[0mSuccessfully installed AutoROM.accept-rom-license-0.6.0 ale-py-0.7.4 autorom-0.4.2 gym-0.21.0 huggingface-hub-0.13.3 huggingface_sb3-2.2.4 importlib-metadata-4.13.0 libtorrent-2.0.7 panda_gym-2.0.0 pybullet-3.2.5 pyglet-1.5.1 stable-baselines3-1.7.0\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "import pybullet_envs\n", + "import panda_gym\n", + "import gym\n", + "\n", + "import os\n", + "\n", + "from huggingface_sb3 import load_from_hub, package_to_hub\n", + "\n", + "from stable_baselines3 import A2C\n", + "from stable_baselines3.common.evaluation import evaluate_policy\n", + "from stable_baselines3.common.vec_env import DummyVecEnv, VecNormalize\n", + "from stable_baselines3.common.env_util import make_vec_env\n", + "\n", + "from huggingface_hub import notebook_login" + ], + "metadata": { + "id": "6IDpBrjKLeaZ" + }, + "execution_count": 5, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "env_id = \"AntBulletEnv-v0\"" + ], + "metadata": { + "id": "MusmLipTSMoQ" + }, + "execution_count": 27, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "env = make_vec_env(env_id, n_envs=4)\n", + "\n", + "env = VecNormalize(env, norm_obs=True, norm_reward=True, clip_obs=10.)\n", + "\n", + "# Get the state space and action space\n", + "s_size = env.observation_space.shape[0]\n", + "a_size = env.action_space" + ], + "metadata": { + "id": "QB16uOceSAJk" + }, + "execution_count": 34, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "model = A2C(policy = \"MlpPolicy\",\n", + " env = env,\n", + " gae_lambda = 0.9,\n", + " gamma = 0.99,\n", + " learning_rate = 0.000969,\n", + " max_grad_norm = 0.5,\n", + " n_steps = 8,\n", + " vf_coef = 0.4,\n", + " ent_coef = 0.0,\n", + " policy_kwargs=dict(\n", + " log_std_init=-2, ortho_init=False),\n", + " normalize_advantage=False,\n", + " use_rms_prop= True,\n", + " use_sde= True,\n", + " verbose=1)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "f_lLTrXnSE8i", + "outputId": "884f5e4b-2abf-4788-b063-5284d9b66970" + }, + "execution_count": 11, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Using cuda device\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "model.learn(3_000_000)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "2Cpuk5HISTB4", + "outputId": "1696f7fa-9c9a-4f31-f35b-de57cc3b79af" + }, + "execution_count": 12, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\u001b[1;30;43mStreaming output truncated to the last 5000 lines.\u001b[0m\n", + "| time/ | |\n", + "| fps | 503 |\n", + "| iterations | 66000 |\n", + "| time_elapsed | 4196 |\n", + "| total_timesteps | 2112000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.94 |\n", + "| explained_variance | 0.527 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 65999 |\n", + "| policy_loss | -0.0793 |\n", + "| std | 0.0439 |\n", + "| value_loss | 0.00688 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 982 |\n", + "| ep_rew_mean | 837 |\n", + "| time/ | |\n", + "| fps | 503 |\n", + "| iterations | 66100 |\n", + "| time_elapsed | 4201 |\n", + "| total_timesteps | 2115200 |\n", + "| train/ | |\n", + "| entropy_loss | -1.87 |\n", + "| explained_variance | 0.991 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 66099 |\n", + "| policy_loss | 0.226 |\n", + "| std | 0.0441 |\n", + "| value_loss | 0.00733 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 982 |\n", + "| ep_rew_mean | 831 |\n", + "| time/ | |\n", + "| fps | 503 |\n", + "| iterations | 66200 |\n", + "| time_elapsed | 4208 |\n", + "| total_timesteps | 2118400 |\n", + "| train/ | |\n", + "| entropy_loss | -1.93 |\n", + "| explained_variance | 0.992 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 66199 |\n", + "| policy_loss | -0.0212 |\n", + "| std | 0.0439 |\n", + "| value_loss | 0.00169 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 982 |\n", + "| ep_rew_mean | 826 |\n", + "| time/ | |\n", + "| fps | 503 |\n", + "| iterations | 66300 |\n", + "| time_elapsed | 4213 |\n", + "| total_timesteps | 2121600 |\n", + "| train/ | |\n", + "| entropy_loss | -1.91 |\n", + "| explained_variance | 0.949 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 66299 |\n", + "| policy_loss | 0.0412 |\n", + "| std | 0.0439 |\n", + "| value_loss | 0.00611 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 982 |\n", + "| ep_rew_mean | 824 |\n", + "| time/ | |\n", + "| fps | 503 |\n", + "| iterations | 66400 |\n", + "| time_elapsed | 4219 |\n", + "| total_timesteps | 2124800 |\n", + "| train/ | |\n", + "| entropy_loss | -1.85 |\n", + "| explained_variance | 0.945 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 66399 |\n", + "| policy_loss | -0.0489 |\n", + "| std | 0.044 |\n", + "| value_loss | 0.0159 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 982 |\n", + "| ep_rew_mean | 828 |\n", + "| time/ | |\n", + "| fps | 503 |\n", + "| iterations | 66500 |\n", + "| time_elapsed | 4225 |\n", + "| total_timesteps | 2128000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.88 |\n", + "| explained_variance | 1 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 66499 |\n", + "| policy_loss | 0.0185 |\n", + "| std | 0.0441 |\n", + "| value_loss | 0.000218 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 973 |\n", + "| ep_rew_mean | 805 |\n", + "| time/ | |\n", + "| fps | 503 |\n", + "| iterations | 66600 |\n", + "| time_elapsed | 4230 |\n", + "| total_timesteps | 2131200 |\n", + "| train/ | |\n", + "| entropy_loss | -1.6 |\n", + "| explained_variance | 0.983 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 66599 |\n", + "| policy_loss | -0.0359 |\n", + "| std | 0.0441 |\n", + "| value_loss | 0.00375 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 973 |\n", + "| ep_rew_mean | 789 |\n", + "| time/ | |\n", + "| fps | 503 |\n", + "| iterations | 66700 |\n", + "| time_elapsed | 4237 |\n", + "| total_timesteps | 2134400 |\n", + "| train/ | |\n", + "| entropy_loss | -1.78 |\n", + "| explained_variance | 0.96 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 66699 |\n", + "| policy_loss | 0.0097 |\n", + "| std | 0.0441 |\n", + "| value_loss | 0.00218 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 973 |\n", + "| ep_rew_mean | 783 |\n", + "| time/ | |\n", + "| fps | 503 |\n", + "| iterations | 66800 |\n", + "| time_elapsed | 4243 |\n", + "| total_timesteps | 2137600 |\n", + "| train/ | |\n", + "| entropy_loss | -1.97 |\n", + "| explained_variance | 0.998 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 66799 |\n", + "| policy_loss | -0.00205 |\n", + "| std | 0.0443 |\n", + "| value_loss | 0.00132 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 973 |\n", + "| ep_rew_mean | 766 |\n", + "| time/ | |\n", + "| fps | 503 |\n", + "| iterations | 66900 |\n", + "| time_elapsed | 4249 |\n", + "| total_timesteps | 2140800 |\n", + "| train/ | |\n", + "| entropy_loss | -1.98 |\n", + "| explained_variance | 0.917 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 66899 |\n", + "| policy_loss | -0.158 |\n", + "| std | 0.0438 |\n", + "| value_loss | 0.00821 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 973 |\n", + "| ep_rew_mean | 759 |\n", + "| time/ | |\n", + "| fps | 503 |\n", + "| iterations | 67000 |\n", + "| time_elapsed | 4257 |\n", + "| total_timesteps | 2144000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.04 |\n", + "| explained_variance | 0.973 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 66999 |\n", + "| policy_loss | 0.128 |\n", + "| std | 0.0441 |\n", + "| value_loss | 0.00298 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 964 |\n", + "| ep_rew_mean | 728 |\n", + "| time/ | |\n", + "| fps | 503 |\n", + "| iterations | 67100 |\n", + "| time_elapsed | 4262 |\n", + "| total_timesteps | 2147200 |\n", + "| train/ | |\n", + "| entropy_loss | -1.8 |\n", + "| explained_variance | 0.998 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 67099 |\n", + "| policy_loss | -0.0328 |\n", + "| std | 0.044 |\n", + "| value_loss | 0.00158 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 958 |\n", + "| ep_rew_mean | 706 |\n", + "| time/ | |\n", + "| fps | 503 |\n", + "| iterations | 67200 |\n", + "| time_elapsed | 4268 |\n", + "| total_timesteps | 2150400 |\n", + "| train/ | |\n", + "| entropy_loss | -1.79 |\n", + "| explained_variance | 0.995 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 67199 |\n", + "| policy_loss | -0.00767 |\n", + "| std | 0.0438 |\n", + "| value_loss | 0.000988 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 955 |\n", + "| ep_rew_mean | 703 |\n", + "| time/ | |\n", + "| fps | 503 |\n", + "| iterations | 67300 |\n", + "| time_elapsed | 4274 |\n", + "| total_timesteps | 2153600 |\n", + "| train/ | |\n", + "| entropy_loss | -1.96 |\n", + "| explained_variance | 0.991 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 67299 |\n", + "| policy_loss | -0.0175 |\n", + "| std | 0.0437 |\n", + "| value_loss | 0.0039 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 955 |\n", + "| ep_rew_mean | 697 |\n", + "| time/ | |\n", + "| fps | 503 |\n", + "| iterations | 67400 |\n", + "| time_elapsed | 4279 |\n", + "| total_timesteps | 2156800 |\n", + "| train/ | |\n", + "| entropy_loss | -1.82 |\n", + "| explained_variance | 0.676 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 67399 |\n", + "| policy_loss | -0.055 |\n", + "| std | 0.0438 |\n", + "| value_loss | 0.00452 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 955 |\n", + "| ep_rew_mean | 694 |\n", + "| time/ | |\n", + "| fps | 503 |\n", + "| iterations | 67500 |\n", + "| time_elapsed | 4286 |\n", + "| total_timesteps | 2160000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.84 |\n", + "| explained_variance | 0.992 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 67499 |\n", + "| policy_loss | -0.0122 |\n", + "| std | 0.0438 |\n", + "| value_loss | 0.00669 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 955 |\n", + "| ep_rew_mean | 683 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 67600 |\n", + "| time_elapsed | 4291 |\n", + "| total_timesteps | 2163200 |\n", + "| train/ | |\n", + "| entropy_loss | -1.65 |\n", + "| explained_variance | 0.999 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 67599 |\n", + "| policy_loss | -0.0261 |\n", + "| std | 0.0438 |\n", + "| value_loss | 0.000684 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 955 |\n", + "| ep_rew_mean | 678 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 67700 |\n", + "| time_elapsed | 4296 |\n", + "| total_timesteps | 2166400 |\n", + "| train/ | |\n", + "| entropy_loss | -1.54 |\n", + "| explained_variance | 0.984 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 67699 |\n", + "| policy_loss | -0.0906 |\n", + "| std | 0.0437 |\n", + "| value_loss | 0.00372 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 964 |\n", + "| ep_rew_mean | 668 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 67800 |\n", + "| time_elapsed | 4303 |\n", + "| total_timesteps | 2169600 |\n", + "| train/ | |\n", + "| entropy_loss | -1.26 |\n", + "| explained_variance | 0.995 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 67799 |\n", + "| policy_loss | -0.0175 |\n", + "| std | 0.0438 |\n", + "| value_loss | 0.000976 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 964 |\n", + "| ep_rew_mean | 651 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 67900 |\n", + "| time_elapsed | 4308 |\n", + "| total_timesteps | 2172800 |\n", + "| train/ | |\n", + "| entropy_loss | -1.5 |\n", + "| explained_variance | 0.817 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 67899 |\n", + "| policy_loss | 0.068 |\n", + "| std | 0.0436 |\n", + "| value_loss | 0.00554 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 964 |\n", + "| ep_rew_mean | 648 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 68000 |\n", + "| time_elapsed | 4315 |\n", + "| total_timesteps | 2176000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.68 |\n", + "| explained_variance | 0.778 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 67999 |\n", + "| policy_loss | -0.0073 |\n", + "| std | 0.0436 |\n", + "| value_loss | 0.000977 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 964 |\n", + "| ep_rew_mean | 626 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 68100 |\n", + "| time_elapsed | 4322 |\n", + "| total_timesteps | 2179200 |\n", + "| train/ | |\n", + "| entropy_loss | -1.47 |\n", + "| explained_variance | 0.986 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 68099 |\n", + "| policy_loss | 0.0278 |\n", + "| std | 0.0435 |\n", + "| value_loss | 0.00246 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 964 |\n", + "| ep_rew_mean | 621 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 68200 |\n", + "| time_elapsed | 4327 |\n", + "| total_timesteps | 2182400 |\n", + "| train/ | |\n", + "| entropy_loss | -1.6 |\n", + "| explained_variance | 0.981 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 68199 |\n", + "| policy_loss | 0.0259 |\n", + "| std | 0.0438 |\n", + "| value_loss | 0.000482 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 964 |\n", + "| ep_rew_mean | 606 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 68300 |\n", + "| time_elapsed | 4334 |\n", + "| total_timesteps | 2185600 |\n", + "| train/ | |\n", + "| entropy_loss | -1.57 |\n", + "| explained_variance | 0.985 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 68299 |\n", + "| policy_loss | 0.0183 |\n", + "| std | 0.044 |\n", + "| value_loss | 0.00143 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 964 |\n", + "| ep_rew_mean | 605 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 68400 |\n", + "| time_elapsed | 4340 |\n", + "| total_timesteps | 2188800 |\n", + "| train/ | |\n", + "| entropy_loss | -1.68 |\n", + "| explained_variance | 0.975 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 68399 |\n", + "| policy_loss | -0.18 |\n", + "| std | 0.044 |\n", + "| value_loss | 0.00996 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 964 |\n", + "| ep_rew_mean | 613 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 68500 |\n", + "| time_elapsed | 4345 |\n", + "| total_timesteps | 2192000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.47 |\n", + "| explained_variance | 0.98 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 68499 |\n", + "| policy_loss | 0.0037 |\n", + "| std | 0.0441 |\n", + "| value_loss | 0.000122 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 964 |\n", + "| ep_rew_mean | 601 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 68600 |\n", + "| time_elapsed | 4351 |\n", + "| total_timesteps | 2195200 |\n", + "| train/ | |\n", + "| entropy_loss | -1.89 |\n", + "| explained_variance | 0.967 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 68599 |\n", + "| policy_loss | -0.0339 |\n", + "| std | 0.044 |\n", + "| value_loss | 0.00105 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 964 |\n", + "| ep_rew_mean | 614 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 68700 |\n", + "| time_elapsed | 4356 |\n", + "| total_timesteps | 2198400 |\n", + "| train/ | |\n", + "| entropy_loss | -1.42 |\n", + "| explained_variance | 0.964 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 68699 |\n", + "| policy_loss | 0.0549 |\n", + "| std | 0.0441 |\n", + "| value_loss | 0.00324 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 964 |\n", + "| ep_rew_mean | 623 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 68800 |\n", + "| time_elapsed | 4362 |\n", + "| total_timesteps | 2201600 |\n", + "| train/ | |\n", + "| entropy_loss | -1.69 |\n", + "| explained_variance | 0.984 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 68799 |\n", + "| policy_loss | 0.0436 |\n", + "| std | 0.044 |\n", + "| value_loss | 0.00112 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 964 |\n", + "| ep_rew_mean | 626 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 68900 |\n", + "| time_elapsed | 4368 |\n", + "| total_timesteps | 2204800 |\n", + "| train/ | |\n", + "| entropy_loss | -1.78 |\n", + "| explained_variance | 0.995 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 68899 |\n", + "| policy_loss | 0.0282 |\n", + "| std | 0.0437 |\n", + "| value_loss | 0.00188 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 973 |\n", + "| ep_rew_mean | 637 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 69000 |\n", + "| time_elapsed | 4373 |\n", + "| total_timesteps | 2208000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.65 |\n", + "| explained_variance | 0.99 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 68999 |\n", + "| policy_loss | -0.0223 |\n", + "| std | 0.0438 |\n", + "| value_loss | 0.00153 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 973 |\n", + "| ep_rew_mean | 642 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 69100 |\n", + "| time_elapsed | 4379 |\n", + "| total_timesteps | 2211200 |\n", + "| train/ | |\n", + "| entropy_loss | -1.69 |\n", + "| explained_variance | 0.901 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 69099 |\n", + "| policy_loss | -0.0424 |\n", + "| std | 0.0438 |\n", + "| value_loss | 0.0126 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 973 |\n", + "| ep_rew_mean | 641 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 69200 |\n", + "| time_elapsed | 4386 |\n", + "| total_timesteps | 2214400 |\n", + "| train/ | |\n", + "| entropy_loss | -1.79 |\n", + "| explained_variance | 0.956 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 69199 |\n", + "| policy_loss | -0.106 |\n", + "| std | 0.044 |\n", + "| value_loss | 0.0174 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 973 |\n", + "| ep_rew_mean | 652 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 69300 |\n", + "| time_elapsed | 4392 |\n", + "| total_timesteps | 2217600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.04 |\n", + "| explained_variance | 0.978 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 69299 |\n", + "| policy_loss | -0.0494 |\n", + "| std | 0.0442 |\n", + "| value_loss | 0.00529 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 973 |\n", + "| ep_rew_mean | 658 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 69400 |\n", + "| time_elapsed | 4399 |\n", + "| total_timesteps | 2220800 |\n", + "| train/ | |\n", + "| entropy_loss | -2 |\n", + "| explained_variance | 0.992 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 69399 |\n", + "| policy_loss | 0.0268 |\n", + "| std | 0.0442 |\n", + "| value_loss | 0.0046 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 973 |\n", + "| ep_rew_mean | 660 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 69500 |\n", + "| time_elapsed | 4404 |\n", + "| total_timesteps | 2224000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.54 |\n", + "| explained_variance | 0.997 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 69499 |\n", + "| policy_loss | -0.0375 |\n", + "| std | 0.044 |\n", + "| value_loss | 0.000709 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 982 |\n", + "| ep_rew_mean | 673 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 69600 |\n", + "| time_elapsed | 4410 |\n", + "| total_timesteps | 2227200 |\n", + "| train/ | |\n", + "| entropy_loss | -1.85 |\n", + "| explained_variance | 0.994 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 69599 |\n", + "| policy_loss | -0.0708 |\n", + "| std | 0.044 |\n", + "| value_loss | 0.00258 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 982 |\n", + "| ep_rew_mean | 683 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 69700 |\n", + "| time_elapsed | 4416 |\n", + "| total_timesteps | 2230400 |\n", + "| train/ | |\n", + "| entropy_loss | -2 |\n", + "| explained_variance | 0.973 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 69699 |\n", + "| policy_loss | -0.0366 |\n", + "| std | 0.0444 |\n", + "| value_loss | 0.000965 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 982 |\n", + "| ep_rew_mean | 678 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 69800 |\n", + "| time_elapsed | 4421 |\n", + "| total_timesteps | 2233600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.01 |\n", + "| explained_variance | 0.99 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 69799 |\n", + "| policy_loss | -0.0818 |\n", + "| std | 0.0444 |\n", + "| value_loss | 0.00552 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 982 |\n", + "| ep_rew_mean | 674 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 69900 |\n", + "| time_elapsed | 4428 |\n", + "| total_timesteps | 2236800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.09 |\n", + "| explained_variance | 0.991 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 69899 |\n", + "| policy_loss | -0.0564 |\n", + "| std | 0.0446 |\n", + "| value_loss | 0.00459 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 982 |\n", + "| ep_rew_mean | 675 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 70000 |\n", + "| time_elapsed | 4433 |\n", + "| total_timesteps | 2240000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.15 |\n", + "| explained_variance | 0.957 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 69999 |\n", + "| policy_loss | -0.0619 |\n", + "| std | 0.0448 |\n", + "| value_loss | 0.0158 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 982 |\n", + "| ep_rew_mean | 674 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 70100 |\n", + "| time_elapsed | 4438 |\n", + "| total_timesteps | 2243200 |\n", + "| train/ | |\n", + "| entropy_loss | -2 |\n", + "| explained_variance | 0.979 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 70099 |\n", + "| policy_loss | 0.0759 |\n", + "| std | 0.0447 |\n", + "| value_loss | 0.00615 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 991 |\n", + "| ep_rew_mean | 683 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 70200 |\n", + "| time_elapsed | 4447 |\n", + "| total_timesteps | 2246400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.16 |\n", + "| explained_variance | 0.994 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 70199 |\n", + "| policy_loss | 0.0403 |\n", + "| std | 0.0449 |\n", + "| value_loss | 0.00667 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 988 |\n", + "| ep_rew_mean | 690 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 70300 |\n", + "| time_elapsed | 4452 |\n", + "| total_timesteps | 2249600 |\n", + "| train/ | |\n", + "| entropy_loss | -1.92 |\n", + "| explained_variance | 0.998 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 70299 |\n", + "| policy_loss | 0.00251 |\n", + "| std | 0.0448 |\n", + "| value_loss | 0.00112 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 991 |\n", + "| ep_rew_mean | 696 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 70400 |\n", + "| time_elapsed | 4461 |\n", + "| total_timesteps | 2252800 |\n", + "| train/ | |\n", + "| entropy_loss | -1.92 |\n", + "| explained_variance | 0.98 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 70399 |\n", + "| policy_loss | -0.0402 |\n", + "| std | 0.0448 |\n", + "| value_loss | 0.00138 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 991 |\n", + "| ep_rew_mean | 690 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 70500 |\n", + "| time_elapsed | 4466 |\n", + "| total_timesteps | 2256000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.09 |\n", + "| explained_variance | 0.997 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 70499 |\n", + "| policy_loss | -0.0369 |\n", + "| std | 0.0449 |\n", + "| value_loss | 0.00421 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 991 |\n", + "| ep_rew_mean | 694 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 70600 |\n", + "| time_elapsed | 4471 |\n", + "| total_timesteps | 2259200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.07 |\n", + "| explained_variance | 0.986 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 70599 |\n", + "| policy_loss | -0.169 |\n", + "| std | 0.045 |\n", + "| value_loss | 0.00936 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 991 |\n", + "| ep_rew_mean | 700 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 70700 |\n", + "| time_elapsed | 4478 |\n", + "| total_timesteps | 2262400 |\n", + "| train/ | |\n", + "| entropy_loss | -1.81 |\n", + "| explained_variance | 0.972 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 70699 |\n", + "| policy_loss | -0.0917 |\n", + "| std | 0.0448 |\n", + "| value_loss | 0.0118 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 991 |\n", + "| ep_rew_mean | 709 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 70800 |\n", + "| time_elapsed | 4483 |\n", + "| total_timesteps | 2265600 |\n", + "| train/ | |\n", + "| entropy_loss | -1.86 |\n", + "| explained_variance | 0.974 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 70799 |\n", + "| policy_loss | -0.171 |\n", + "| std | 0.0446 |\n", + "| value_loss | 0.00445 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 991 |\n", + "| ep_rew_mean | 709 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 70900 |\n", + "| time_elapsed | 4489 |\n", + "| total_timesteps | 2268800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.05 |\n", + "| explained_variance | 0.993 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 70899 |\n", + "| policy_loss | 0.0212 |\n", + "| std | 0.0447 |\n", + "| value_loss | 0.00244 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 991 |\n", + "| ep_rew_mean | 721 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 71000 |\n", + "| time_elapsed | 4495 |\n", + "| total_timesteps | 2272000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.74 |\n", + "| explained_variance | 0.601 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 70999 |\n", + "| policy_loss | -0.00785 |\n", + "| std | 0.0449 |\n", + "| value_loss | 0.00662 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 991 |\n", + "| ep_rew_mean | 728 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 71100 |\n", + "| time_elapsed | 4501 |\n", + "| total_timesteps | 2275200 |\n", + "| train/ | |\n", + "| entropy_loss | -1.83 |\n", + "| explained_variance | 0.968 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 71099 |\n", + "| policy_loss | 0.0329 |\n", + "| std | 0.0449 |\n", + "| value_loss | 0.00158 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 991 |\n", + "| ep_rew_mean | 726 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 71200 |\n", + "| time_elapsed | 4508 |\n", + "| total_timesteps | 2278400 |\n", + "| train/ | |\n", + "| entropy_loss | -1.72 |\n", + "| explained_variance | 0.977 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 71199 |\n", + "| policy_loss | 0.0111 |\n", + "| std | 0.0449 |\n", + "| value_loss | 0.00331 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 974 |\n", + "| ep_rew_mean | 714 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 71300 |\n", + "| time_elapsed | 4513 |\n", + "| total_timesteps | 2281600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.03 |\n", + "| explained_variance | 0.993 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 71299 |\n", + "| policy_loss | 0.0158 |\n", + "| std | 0.0448 |\n", + "| value_loss | 0.00219 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 974 |\n", + "| ep_rew_mean | 714 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 71400 |\n", + "| time_elapsed | 4518 |\n", + "| total_timesteps | 2284800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.01 |\n", + "| explained_variance | 0.911 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 71399 |\n", + "| policy_loss | 0.103 |\n", + "| std | 0.0449 |\n", + "| value_loss | 0.00885 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 974 |\n", + "| ep_rew_mean | 711 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 71500 |\n", + "| time_elapsed | 4527 |\n", + "| total_timesteps | 2288000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.06 |\n", + "| explained_variance | 0.98 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 71499 |\n", + "| policy_loss | -0.00293 |\n", + "| std | 0.0448 |\n", + "| value_loss | 0.000287 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 974 |\n", + "| ep_rew_mean | 703 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 71600 |\n", + "| time_elapsed | 4532 |\n", + "| total_timesteps | 2291200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.2 |\n", + "| explained_variance | 0.972 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 71599 |\n", + "| policy_loss | -0.0277 |\n", + "| std | 0.0447 |\n", + "| value_loss | 0.0009 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 974 |\n", + "| ep_rew_mean | 701 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 71700 |\n", + "| time_elapsed | 4539 |\n", + "| total_timesteps | 2294400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.17 |\n", + "| explained_variance | 0.979 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 71699 |\n", + "| policy_loss | -0.0143 |\n", + "| std | 0.0444 |\n", + "| value_loss | 0.000387 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 966 |\n", + "| ep_rew_mean | 682 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 71800 |\n", + "| time_elapsed | 4544 |\n", + "| total_timesteps | 2297600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.1 |\n", + "| explained_variance | 0.999 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 71799 |\n", + "| policy_loss | -0.0162 |\n", + "| std | 0.0443 |\n", + "| value_loss | 0.000935 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 966 |\n", + "| ep_rew_mean | 669 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 71900 |\n", + "| time_elapsed | 4550 |\n", + "| total_timesteps | 2300800 |\n", + "| train/ | |\n", + "| entropy_loss | -1.81 |\n", + "| explained_variance | 0.981 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 71899 |\n", + "| policy_loss | 0.00858 |\n", + "| std | 0.0444 |\n", + "| value_loss | 0.0011 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 966 |\n", + "| ep_rew_mean | 666 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 72000 |\n", + "| time_elapsed | 4556 |\n", + "| total_timesteps | 2304000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.77 |\n", + "| explained_variance | 0.995 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 71999 |\n", + "| policy_loss | -0.056 |\n", + "| std | 0.0444 |\n", + "| value_loss | 0.00265 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 966 |\n", + "| ep_rew_mean | 656 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 72100 |\n", + "| time_elapsed | 4562 |\n", + "| total_timesteps | 2307200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.04 |\n", + "| explained_variance | 0.998 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 72099 |\n", + "| policy_loss | 0.00753 |\n", + "| std | 0.0442 |\n", + "| value_loss | 0.000321 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 966 |\n", + "| ep_rew_mean | 645 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 72200 |\n", + "| time_elapsed | 4569 |\n", + "| total_timesteps | 2310400 |\n", + "| train/ | |\n", + "| entropy_loss | -1.86 |\n", + "| explained_variance | 1 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 72199 |\n", + "| policy_loss | 0.00274 |\n", + "| std | 0.0443 |\n", + "| value_loss | 1.86e-05 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 966 |\n", + "| ep_rew_mean | 636 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 72300 |\n", + "| time_elapsed | 4574 |\n", + "| total_timesteps | 2313600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.01 |\n", + "| explained_variance | 0.999 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 72299 |\n", + "| policy_loss | -0.0102 |\n", + "| std | 0.0442 |\n", + "| value_loss | 0.000217 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 966 |\n", + "| ep_rew_mean | 624 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 72400 |\n", + "| time_elapsed | 4579 |\n", + "| total_timesteps | 2316800 |\n", + "| train/ | |\n", + "| entropy_loss | -1.96 |\n", + "| explained_variance | 0.972 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 72399 |\n", + "| policy_loss | 0.0648 |\n", + "| std | 0.0441 |\n", + "| value_loss | 0.00371 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 966 |\n", + "| ep_rew_mean | 618 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 72500 |\n", + "| time_elapsed | 4586 |\n", + "| total_timesteps | 2320000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.71 |\n", + "| explained_variance | 0.928 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 72499 |\n", + "| policy_loss | -0.00488 |\n", + "| std | 0.0441 |\n", + "| value_loss | 0.00173 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 966 |\n", + "| ep_rew_mean | 611 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 72600 |\n", + "| time_elapsed | 4592 |\n", + "| total_timesteps | 2323200 |\n", + "| train/ | |\n", + "| entropy_loss | -1.38 |\n", + "| explained_variance | 0.983 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 72599 |\n", + "| policy_loss | -0.0128 |\n", + "| std | 0.0439 |\n", + "| value_loss | 0.000409 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 966 |\n", + "| ep_rew_mean | 602 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 72700 |\n", + "| time_elapsed | 4600 |\n", + "| total_timesteps | 2326400 |\n", + "| train/ | |\n", + "| entropy_loss | -1.73 |\n", + "| explained_variance | 0.978 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 72699 |\n", + "| policy_loss | -0.0135 |\n", + "| std | 0.0438 |\n", + "| value_loss | 0.000836 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 966 |\n", + "| ep_rew_mean | 607 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 72800 |\n", + "| time_elapsed | 4605 |\n", + "| total_timesteps | 2329600 |\n", + "| train/ | |\n", + "| entropy_loss | -1.9 |\n", + "| explained_variance | 0.999 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 72799 |\n", + "| policy_loss | 0.0181 |\n", + "| std | 0.0438 |\n", + "| value_loss | 0.000441 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 958 |\n", + "| ep_rew_mean | 597 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 72900 |\n", + "| time_elapsed | 4611 |\n", + "| total_timesteps | 2332800 |\n", + "| train/ | |\n", + "| entropy_loss | -1.9 |\n", + "| explained_variance | 0.997 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 72899 |\n", + "| policy_loss | -0.0169 |\n", + "| std | 0.0439 |\n", + "| value_loss | 0.000832 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 958 |\n", + "| ep_rew_mean | 594 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 73000 |\n", + "| time_elapsed | 4618 |\n", + "| total_timesteps | 2336000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.98 |\n", + "| explained_variance | 0.998 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 72999 |\n", + "| policy_loss | -0.0223 |\n", + "| std | 0.0441 |\n", + "| value_loss | 0.00108 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 958 |\n", + "| ep_rew_mean | 597 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 73100 |\n", + "| time_elapsed | 4623 |\n", + "| total_timesteps | 2339200 |\n", + "| train/ | |\n", + "| entropy_loss | -1.77 |\n", + "| explained_variance | 0.976 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 73099 |\n", + "| policy_loss | -0.0312 |\n", + "| std | 0.0441 |\n", + "| value_loss | 0.00283 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 958 |\n", + "| ep_rew_mean | 602 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 73200 |\n", + "| time_elapsed | 4629 |\n", + "| total_timesteps | 2342400 |\n", + "| train/ | |\n", + "| entropy_loss | -1.9 |\n", + "| explained_variance | 0.985 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 73199 |\n", + "| policy_loss | 0.0327 |\n", + "| std | 0.0443 |\n", + "| value_loss | 0.000597 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 958 |\n", + "| ep_rew_mean | 606 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 73300 |\n", + "| time_elapsed | 4635 |\n", + "| total_timesteps | 2345600 |\n", + "| train/ | |\n", + "| entropy_loss | -1.99 |\n", + "| explained_variance | 0.898 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 73299 |\n", + "| policy_loss | -0.0265 |\n", + "| std | 0.0444 |\n", + "| value_loss | 0.00135 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 967 |\n", + "| ep_rew_mean | 614 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 73400 |\n", + "| time_elapsed | 4640 |\n", + "| total_timesteps | 2348800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.03 |\n", + "| explained_variance | 0.988 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 73399 |\n", + "| policy_loss | 0.0502 |\n", + "| std | 0.0445 |\n", + "| value_loss | 0.00135 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 967 |\n", + "| ep_rew_mean | 621 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 73500 |\n", + "| time_elapsed | 4647 |\n", + "| total_timesteps | 2352000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.12 |\n", + "| explained_variance | 0.893 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 73499 |\n", + "| policy_loss | 0.0225 |\n", + "| std | 0.0449 |\n", + "| value_loss | 0.0071 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 967 |\n", + "| ep_rew_mean | 623 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 73600 |\n", + "| time_elapsed | 4652 |\n", + "| total_timesteps | 2355200 |\n", + "| train/ | |\n", + "| entropy_loss | -1.73 |\n", + "| explained_variance | 0.997 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 73599 |\n", + "| policy_loss | -0.00663 |\n", + "| std | 0.045 |\n", + "| value_loss | 0.000561 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 967 |\n", + "| ep_rew_mean | 623 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 73700 |\n", + "| time_elapsed | 4658 |\n", + "| total_timesteps | 2358400 |\n", + "| train/ | |\n", + "| entropy_loss | -1.99 |\n", + "| explained_variance | 0.897 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 73699 |\n", + "| policy_loss | -0.157 |\n", + "| std | 0.045 |\n", + "| value_loss | 0.00337 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 967 |\n", + "| ep_rew_mean | 625 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 73800 |\n", + "| time_elapsed | 4666 |\n", + "| total_timesteps | 2361600 |\n", + "| train/ | |\n", + "| entropy_loss | -1.89 |\n", + "| explained_variance | 0.97 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 73799 |\n", + "| policy_loss | -0.0149 |\n", + "| std | 0.045 |\n", + "| value_loss | 0.000912 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 967 |\n", + "| ep_rew_mean | 632 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 73900 |\n", + "| time_elapsed | 4671 |\n", + "| total_timesteps | 2364800 |\n", + "| train/ | |\n", + "| entropy_loss | -1.88 |\n", + "| explained_variance | 0.995 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 73899 |\n", + "| policy_loss | -0.0312 |\n", + "| std | 0.0451 |\n", + "| value_loss | 0.0012 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 967 |\n", + "| ep_rew_mean | 631 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 74000 |\n", + "| time_elapsed | 4678 |\n", + "| total_timesteps | 2368000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.15 |\n", + "| explained_variance | 0.996 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 73999 |\n", + "| policy_loss | 0.0126 |\n", + "| std | 0.045 |\n", + "| value_loss | 0.00145 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 967 |\n", + "| ep_rew_mean | 626 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 74100 |\n", + "| time_elapsed | 4684 |\n", + "| total_timesteps | 2371200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.03 |\n", + "| explained_variance | 0.993 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 74099 |\n", + "| policy_loss | 0.0358 |\n", + "| std | 0.0449 |\n", + "| value_loss | 0.00197 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 967 |\n", + "| ep_rew_mean | 629 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 74200 |\n", + "| time_elapsed | 4689 |\n", + "| total_timesteps | 2374400 |\n", + "| train/ | |\n", + "| entropy_loss | -1.96 |\n", + "| explained_variance | 0.956 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 74199 |\n", + "| policy_loss | -0.0295 |\n", + "| std | 0.0451 |\n", + "| value_loss | 0.00385 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 976 |\n", + "| ep_rew_mean | 640 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 74300 |\n", + "| time_elapsed | 4696 |\n", + "| total_timesteps | 2377600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.35 |\n", + "| explained_variance | 0.96 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 74299 |\n", + "| policy_loss | -0.00894 |\n", + "| std | 0.0452 |\n", + "| value_loss | 0.002 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 976 |\n", + "| ep_rew_mean | 646 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 74400 |\n", + "| time_elapsed | 4701 |\n", + "| total_timesteps | 2380800 |\n", + "| train/ | |\n", + "| entropy_loss | -1.92 |\n", + "| explained_variance | 0.927 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 74399 |\n", + "| policy_loss | -0.0588 |\n", + "| std | 0.045 |\n", + "| value_loss | 0.00165 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 976 |\n", + "| ep_rew_mean | 654 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 74500 |\n", + "| time_elapsed | 4707 |\n", + "| total_timesteps | 2384000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.23 |\n", + "| explained_variance | 0.996 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 74499 |\n", + "| policy_loss | -0.00752 |\n", + "| std | 0.0451 |\n", + "| value_loss | 0.00116 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 976 |\n", + "| ep_rew_mean | 658 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 74600 |\n", + "| time_elapsed | 4713 |\n", + "| total_timesteps | 2387200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.41 |\n", + "| explained_variance | 0.994 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 74599 |\n", + "| policy_loss | -0.0517 |\n", + "| std | 0.0451 |\n", + "| value_loss | 0.00112 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 976 |\n", + "| ep_rew_mean | 667 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 74700 |\n", + "| time_elapsed | 4720 |\n", + "| total_timesteps | 2390400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.08 |\n", + "| explained_variance | 0.996 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 74699 |\n", + "| policy_loss | 0.0289 |\n", + "| std | 0.045 |\n", + "| value_loss | 0.00301 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 984 |\n", + "| ep_rew_mean | 677 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 74800 |\n", + "| time_elapsed | 4727 |\n", + "| total_timesteps | 2393600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.41 |\n", + "| explained_variance | 0.991 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 74799 |\n", + "| policy_loss | 0.0674 |\n", + "| std | 0.045 |\n", + "| value_loss | 0.0016 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 984 |\n", + "| ep_rew_mean | 683 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 74900 |\n", + "| time_elapsed | 4734 |\n", + "| total_timesteps | 2396800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.09 |\n", + "| explained_variance | 0.966 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 74899 |\n", + "| policy_loss | 0.0196 |\n", + "| std | 0.0452 |\n", + "| value_loss | 0.00546 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 984 |\n", + "| ep_rew_mean | 691 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 75000 |\n", + "| time_elapsed | 4741 |\n", + "| total_timesteps | 2400000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.83 |\n", + "| explained_variance | 0.928 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 74999 |\n", + "| policy_loss | -0.0283 |\n", + "| std | 0.045 |\n", + "| value_loss | 0.0036 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 984 |\n", + "| ep_rew_mean | 698 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 75100 |\n", + "| time_elapsed | 4747 |\n", + "| total_timesteps | 2403200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.15 |\n", + "| explained_variance | 0.888 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 75099 |\n", + "| policy_loss | 0.00994 |\n", + "| std | 0.0452 |\n", + "| value_loss | 0.000885 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 984 |\n", + "| ep_rew_mean | 697 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 75200 |\n", + "| time_elapsed | 4752 |\n", + "| total_timesteps | 2406400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.19 |\n", + "| explained_variance | 0.981 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 75199 |\n", + "| policy_loss | 0.00912 |\n", + "| std | 0.0453 |\n", + "| value_loss | 0.00309 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 984 |\n", + "| ep_rew_mean | 696 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 75300 |\n", + "| time_elapsed | 4759 |\n", + "| total_timesteps | 2409600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.15 |\n", + "| explained_variance | 0.996 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 75299 |\n", + "| policy_loss | 0.00114 |\n", + "| std | 0.0452 |\n", + "| value_loss | 0.000293 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 984 |\n", + "| ep_rew_mean | 695 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 75400 |\n", + "| time_elapsed | 4764 |\n", + "| total_timesteps | 2412800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.05 |\n", + "| explained_variance | 0.986 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 75399 |\n", + "| policy_loss | -0.0291 |\n", + "| std | 0.0452 |\n", + "| value_loss | 0.00337 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 984 |\n", + "| ep_rew_mean | 689 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 75500 |\n", + "| time_elapsed | 4771 |\n", + "| total_timesteps | 2416000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.74 |\n", + "| explained_variance | 0.974 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 75499 |\n", + "| policy_loss | -0.0515 |\n", + "| std | 0.0454 |\n", + "| value_loss | 0.00145 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 984 |\n", + "| ep_rew_mean | 692 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 75600 |\n", + "| time_elapsed | 4776 |\n", + "| total_timesteps | 2419200 |\n", + "| train/ | |\n", + "| entropy_loss | -2 |\n", + "| explained_variance | 0.992 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 75599 |\n", + "| policy_loss | 0.0203 |\n", + "| std | 0.0455 |\n", + "| value_loss | 0.000651 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 984 |\n", + "| ep_rew_mean | 687 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 75700 |\n", + "| time_elapsed | 4781 |\n", + "| total_timesteps | 2422400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.4 |\n", + "| explained_variance | 0.842 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 75699 |\n", + "| policy_loss | 0.00037 |\n", + "| std | 0.0453 |\n", + "| value_loss | 0.000796 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 984 |\n", + "| ep_rew_mean | 683 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 75800 |\n", + "| time_elapsed | 4788 |\n", + "| total_timesteps | 2425600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.33 |\n", + "| explained_variance | 0.979 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 75799 |\n", + "| policy_loss | 0.0412 |\n", + "| std | 0.0454 |\n", + "| value_loss | 0.00116 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 984 |\n", + "| ep_rew_mean | 680 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 75900 |\n", + "| time_elapsed | 4793 |\n", + "| total_timesteps | 2428800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.24 |\n", + "| explained_variance | 0.987 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 75899 |\n", + "| policy_loss | 0.00499 |\n", + "| std | 0.0457 |\n", + "| value_loss | 0.000968 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 992 |\n", + "| ep_rew_mean | 679 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 76000 |\n", + "| time_elapsed | 4800 |\n", + "| total_timesteps | 2432000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.88 |\n", + "| explained_variance | 0.986 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 75999 |\n", + "| policy_loss | -0.0398 |\n", + "| std | 0.0457 |\n", + "| value_loss | 0.000733 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 992 |\n", + "| ep_rew_mean | 678 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 76100 |\n", + "| time_elapsed | 4808 |\n", + "| total_timesteps | 2435200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.07 |\n", + "| explained_variance | 0.984 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 76099 |\n", + "| policy_loss | -0.0276 |\n", + "| std | 0.0457 |\n", + "| value_loss | 0.0017 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 992 |\n", + "| ep_rew_mean | 677 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 76200 |\n", + "| time_elapsed | 4813 |\n", + "| total_timesteps | 2438400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.24 |\n", + "| explained_variance | 0.998 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 76199 |\n", + "| policy_loss | 0.0099 |\n", + "| std | 0.0461 |\n", + "| value_loss | 0.00137 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 992 |\n", + "| ep_rew_mean | 672 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 76300 |\n", + "| time_elapsed | 4820 |\n", + "| total_timesteps | 2441600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.45 |\n", + "| explained_variance | 0.993 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 76299 |\n", + "| policy_loss | 0.00516 |\n", + "| std | 0.0462 |\n", + "| value_loss | 0.00299 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 992 |\n", + "| ep_rew_mean | 659 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 76400 |\n", + "| time_elapsed | 4825 |\n", + "| total_timesteps | 2444800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.15 |\n", + "| explained_variance | 0.986 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 76399 |\n", + "| policy_loss | 0.0664 |\n", + "| std | 0.0462 |\n", + "| value_loss | 0.00139 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 992 |\n", + "| ep_rew_mean | 649 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 76500 |\n", + "| time_elapsed | 4831 |\n", + "| total_timesteps | 2448000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.17 |\n", + "| explained_variance | 0.979 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 76499 |\n", + "| policy_loss | -0.0358 |\n", + "| std | 0.0462 |\n", + "| value_loss | 0.000589 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 992 |\n", + "| ep_rew_mean | 647 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 76600 |\n", + "| time_elapsed | 4838 |\n", + "| total_timesteps | 2451200 |\n", + "| train/ | |\n", + "| entropy_loss | -1.82 |\n", + "| explained_variance | 0.983 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 76599 |\n", + "| policy_loss | 0.0244 |\n", + "| std | 0.0464 |\n", + "| value_loss | 0.00211 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 992 |\n", + "| ep_rew_mean | 651 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 76700 |\n", + "| time_elapsed | 4843 |\n", + "| total_timesteps | 2454400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.22 |\n", + "| explained_variance | 0.996 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 76699 |\n", + "| policy_loss | -0.0188 |\n", + "| std | 0.0464 |\n", + "| value_loss | 0.00134 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 992 |\n", + "| ep_rew_mean | 643 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 76800 |\n", + "| time_elapsed | 4849 |\n", + "| total_timesteps | 2457600 |\n", + "| train/ | |\n", + "| entropy_loss | -1.84 |\n", + "| explained_variance | 0.967 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 76799 |\n", + "| policy_loss | -0.0137 |\n", + "| std | 0.0461 |\n", + "| value_loss | 0.00131 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 992 |\n", + "| ep_rew_mean | 644 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 76900 |\n", + "| time_elapsed | 4855 |\n", + "| total_timesteps | 2460800 |\n", + "| train/ | |\n", + "| entropy_loss | -1.87 |\n", + "| explained_variance | 0.984 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 76899 |\n", + "| policy_loss | 0.0145 |\n", + "| std | 0.0461 |\n", + "| value_loss | 0.00126 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 992 |\n", + "| ep_rew_mean | 645 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 77000 |\n", + "| time_elapsed | 4860 |\n", + "| total_timesteps | 2464000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.91 |\n", + "| explained_variance | 0.98 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 76999 |\n", + "| policy_loss | 0.0793 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.00223 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 992 |\n", + "| ep_rew_mean | 642 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 77100 |\n", + "| time_elapsed | 4867 |\n", + "| total_timesteps | 2467200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.1 |\n", + "| explained_variance | 0.995 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 77099 |\n", + "| policy_loss | -0.00609 |\n", + "| std | 0.0459 |\n", + "| value_loss | 0.00114 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 992 |\n", + "| ep_rew_mean | 648 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 77200 |\n", + "| time_elapsed | 4874 |\n", + "| total_timesteps | 2470400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.17 |\n", + "| explained_variance | 0.988 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 77199 |\n", + "| policy_loss | 0.000536 |\n", + "| std | 0.0459 |\n", + "| value_loss | 0.000534 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 992 |\n", + "| ep_rew_mean | 654 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 77300 |\n", + "| time_elapsed | 4880 |\n", + "| total_timesteps | 2473600 |\n", + "| train/ | |\n", + "| entropy_loss | -1.98 |\n", + "| explained_variance | 0.963 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 77299 |\n", + "| policy_loss | -0.0296 |\n", + "| std | 0.0458 |\n", + "| value_loss | 0.00367 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 992 |\n", + "| ep_rew_mean | 656 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 77400 |\n", + "| time_elapsed | 4886 |\n", + "| total_timesteps | 2476800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.42 |\n", + "| explained_variance | 0.976 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 77399 |\n", + "| policy_loss | -0.0604 |\n", + "| std | 0.0458 |\n", + "| value_loss | 0.0054 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 661 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 77500 |\n", + "| time_elapsed | 4891 |\n", + "| total_timesteps | 2480000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.11 |\n", + "| explained_variance | 0.978 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 77499 |\n", + "| policy_loss | 0.000675 |\n", + "| std | 0.0457 |\n", + "| value_loss | 0.000454 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 653 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 77600 |\n", + "| time_elapsed | 4898 |\n", + "| total_timesteps | 2483200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.31 |\n", + "| explained_variance | 0.97 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 77599 |\n", + "| policy_loss | -0.0277 |\n", + "| std | 0.0458 |\n", + "| value_loss | 0.00531 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 648 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 77700 |\n", + "| time_elapsed | 4904 |\n", + "| total_timesteps | 2486400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.34 |\n", + "| explained_variance | 0.997 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 77699 |\n", + "| policy_loss | 0.0146 |\n", + "| std | 0.0459 |\n", + "| value_loss | 0.00106 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 652 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 77800 |\n", + "| time_elapsed | 4910 |\n", + "| total_timesteps | 2489600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.36 |\n", + "| explained_variance | 0.928 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 77799 |\n", + "| policy_loss | 0.162 |\n", + "| std | 0.0462 |\n", + "| value_loss | 0.00722 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 643 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 77900 |\n", + "| time_elapsed | 4916 |\n", + "| total_timesteps | 2492800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.25 |\n", + "| explained_variance | 0.943 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 77899 |\n", + "| policy_loss | 0.0674 |\n", + "| std | 0.0462 |\n", + "| value_loss | 0.0043 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 644 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 78000 |\n", + "| time_elapsed | 4921 |\n", + "| total_timesteps | 2496000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.69 |\n", + "| explained_variance | 0.609 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 77999 |\n", + "| policy_loss | 0.0236 |\n", + "| std | 0.0463 |\n", + "| value_loss | 0.000692 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 645 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 78100 |\n", + "| time_elapsed | 4928 |\n", + "| total_timesteps | 2499200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.03 |\n", + "| explained_variance | 0.975 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 78099 |\n", + "| policy_loss | 0.00853 |\n", + "| std | 0.0463 |\n", + "| value_loss | 0.00125 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 640 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 78200 |\n", + "| time_elapsed | 4933 |\n", + "| total_timesteps | 2502400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.16 |\n", + "| explained_variance | 0.996 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 78199 |\n", + "| policy_loss | -0.0337 |\n", + "| std | 0.0464 |\n", + "| value_loss | 0.000615 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 641 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 78300 |\n", + "| time_elapsed | 4938 |\n", + "| total_timesteps | 2505600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.41 |\n", + "| explained_variance | 0.963 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 78299 |\n", + "| policy_loss | -0.103 |\n", + "| std | 0.0465 |\n", + "| value_loss | 0.00805 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 649 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 78400 |\n", + "| time_elapsed | 4947 |\n", + "| total_timesteps | 2508800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.28 |\n", + "| explained_variance | 0.894 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 78399 |\n", + "| policy_loss | 0.0147 |\n", + "| std | 0.0463 |\n", + "| value_loss | 0.00777 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 991 |\n", + "| ep_rew_mean | 643 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 78500 |\n", + "| time_elapsed | 4952 |\n", + "| total_timesteps | 2512000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.94 |\n", + "| explained_variance | 0.994 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 78499 |\n", + "| policy_loss | -0.021 |\n", + "| std | 0.0465 |\n", + "| value_loss | 0.00146 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 991 |\n", + "| ep_rew_mean | 648 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 78600 |\n", + "| time_elapsed | 4959 |\n", + "| total_timesteps | 2515200 |\n", + "| train/ | |\n", + "| entropy_loss | -1.99 |\n", + "| explained_variance | 0.986 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 78599 |\n", + "| policy_loss | -0.0172 |\n", + "| std | 0.0466 |\n", + "| value_loss | 0.000644 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 991 |\n", + "| ep_rew_mean | 652 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 78700 |\n", + "| time_elapsed | 4965 |\n", + "| total_timesteps | 2518400 |\n", + "| train/ | |\n", + "| entropy_loss | -2 |\n", + "| explained_variance | 0.919 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 78699 |\n", + "| policy_loss | 0.0104 |\n", + "| std | 0.0466 |\n", + "| value_loss | 0.00124 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 985 |\n", + "| ep_rew_mean | 656 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 78800 |\n", + "| time_elapsed | 4970 |\n", + "| total_timesteps | 2521600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.2 |\n", + "| explained_variance | 0.964 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 78799 |\n", + "| policy_loss | -0.167 |\n", + "| std | 0.0466 |\n", + "| value_loss | 0.0026 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 985 |\n", + "| ep_rew_mean | 661 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 78900 |\n", + "| time_elapsed | 4977 |\n", + "| total_timesteps | 2524800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.22 |\n", + "| explained_variance | 0.985 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 78899 |\n", + "| policy_loss | -0.00343 |\n", + "| std | 0.0467 |\n", + "| value_loss | 0.00132 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 985 |\n", + "| ep_rew_mean | 665 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 79000 |\n", + "| time_elapsed | 4983 |\n", + "| total_timesteps | 2528000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.33 |\n", + "| explained_variance | 0.998 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 78999 |\n", + "| policy_loss | -0.00256 |\n", + "| std | 0.0468 |\n", + "| value_loss | 0.000372 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 985 |\n", + "| ep_rew_mean | 669 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 79100 |\n", + "| time_elapsed | 4990 |\n", + "| total_timesteps | 2531200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.5 |\n", + "| explained_variance | 0.973 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 79099 |\n", + "| policy_loss | 0.0551 |\n", + "| std | 0.0466 |\n", + "| value_loss | 0.0028 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 985 |\n", + "| ep_rew_mean | 673 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 79200 |\n", + "| time_elapsed | 4997 |\n", + "| total_timesteps | 2534400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.23 |\n", + "| explained_variance | 0.936 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 79199 |\n", + "| policy_loss | 0.048 |\n", + "| std | 0.0467 |\n", + "| value_loss | 0.000711 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 985 |\n", + "| ep_rew_mean | 671 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 79300 |\n", + "| time_elapsed | 5004 |\n", + "| total_timesteps | 2537600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.07 |\n", + "| explained_variance | 0.965 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 79299 |\n", + "| policy_loss | -0.0255 |\n", + "| std | 0.0466 |\n", + "| value_loss | 0.000793 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 985 |\n", + "| ep_rew_mean | 670 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 79400 |\n", + "| time_elapsed | 5010 |\n", + "| total_timesteps | 2540800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.07 |\n", + "| explained_variance | 0.996 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 79399 |\n", + "| policy_loss | -0.00392 |\n", + "| std | 0.0464 |\n", + "| value_loss | 0.000115 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 985 |\n", + "| ep_rew_mean | 677 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 79500 |\n", + "| time_elapsed | 5017 |\n", + "| total_timesteps | 2544000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.2 |\n", + "| explained_variance | 0.988 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 79499 |\n", + "| policy_loss | 0.00371 |\n", + "| std | 0.0465 |\n", + "| value_loss | 0.00104 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 985 |\n", + "| ep_rew_mean | 679 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 79600 |\n", + "| time_elapsed | 5024 |\n", + "| total_timesteps | 2547200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.47 |\n", + "| explained_variance | 0.958 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 79599 |\n", + "| policy_loss | 0.017 |\n", + "| std | 0.0465 |\n", + "| value_loss | 0.00114 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 985 |\n", + "| ep_rew_mean | 673 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 79700 |\n", + "| time_elapsed | 5030 |\n", + "| total_timesteps | 2550400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.29 |\n", + "| explained_variance | 0.962 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 79699 |\n", + "| policy_loss | 0.121 |\n", + "| std | 0.0464 |\n", + "| value_loss | 0.00497 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 985 |\n", + "| ep_rew_mean | 668 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 79800 |\n", + "| time_elapsed | 5037 |\n", + "| total_timesteps | 2553600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.03 |\n", + "| explained_variance | 0.983 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 79799 |\n", + "| policy_loss | 0.0309 |\n", + "| std | 0.0462 |\n", + "| value_loss | 0.00107 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 985 |\n", + "| ep_rew_mean | 668 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 79900 |\n", + "| time_elapsed | 5042 |\n", + "| total_timesteps | 2556800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.1 |\n", + "| explained_variance | 0.983 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 79899 |\n", + "| policy_loss | 0.00469 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.000984 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 985 |\n", + "| ep_rew_mean | 666 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 80000 |\n", + "| time_elapsed | 5048 |\n", + "| total_timesteps | 2560000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.44 |\n", + "| explained_variance | 0.997 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 79999 |\n", + "| policy_loss | 0.0222 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.000477 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 977 |\n", + "| ep_rew_mean | 654 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 80100 |\n", + "| time_elapsed | 5055 |\n", + "| total_timesteps | 2563200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.22 |\n", + "| explained_variance | 0.992 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 80099 |\n", + "| policy_loss | 0.0219 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.000706 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 959 |\n", + "| ep_rew_mean | 638 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 80200 |\n", + "| time_elapsed | 5061 |\n", + "| total_timesteps | 2566400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.21 |\n", + "| explained_variance | 0.983 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 80199 |\n", + "| policy_loss | 0.0332 |\n", + "| std | 0.0461 |\n", + "| value_loss | 0.000815 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 959 |\n", + "| ep_rew_mean | 634 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 80300 |\n", + "| time_elapsed | 5068 |\n", + "| total_timesteps | 2569600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.6 |\n", + "| explained_variance | 0.997 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 80299 |\n", + "| policy_loss | 0.0291 |\n", + "| std | 0.0461 |\n", + "| value_loss | 0.000661 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 959 |\n", + "| ep_rew_mean | 634 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 80400 |\n", + "| time_elapsed | 5074 |\n", + "| total_timesteps | 2572800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.47 |\n", + "| explained_variance | 0.933 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 80399 |\n", + "| policy_loss | -0.0324 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.000976 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 959 |\n", + "| ep_rew_mean | 632 |\n", + "| time/ | |\n", + "| fps | 507 |\n", + "| iterations | 80500 |\n", + "| time_elapsed | 5079 |\n", + "| total_timesteps | 2576000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.22 |\n", + "| explained_variance | 0.901 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 80499 |\n", + "| policy_loss | 0.0194 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.00225 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 959 |\n", + "| ep_rew_mean | 639 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 80600 |\n", + "| time_elapsed | 5089 |\n", + "| total_timesteps | 2579200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.04 |\n", + "| explained_variance | 0.93 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 80599 |\n", + "| policy_loss | -0.0439 |\n", + "| std | 0.0461 |\n", + "| value_loss | 0.00135 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 959 |\n", + "| ep_rew_mean | 643 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 80700 |\n", + "| time_elapsed | 5094 |\n", + "| total_timesteps | 2582400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.23 |\n", + "| explained_variance | 0.955 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 80699 |\n", + "| policy_loss | -0.0186 |\n", + "| std | 0.0462 |\n", + "| value_loss | 0.000578 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 959 |\n", + "| ep_rew_mean | 643 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 80800 |\n", + "| time_elapsed | 5102 |\n", + "| total_timesteps | 2585600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.49 |\n", + "| explained_variance | 0.978 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 80799 |\n", + "| policy_loss | -0.0176 |\n", + "| std | 0.0459 |\n", + "| value_loss | 0.000558 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 959 |\n", + "| ep_rew_mean | 649 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 80900 |\n", + "| time_elapsed | 5107 |\n", + "| total_timesteps | 2588800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.46 |\n", + "| explained_variance | 0.924 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 80899 |\n", + "| policy_loss | -0.0291 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.00048 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 959 |\n", + "| ep_rew_mean | 658 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 81000 |\n", + "| time_elapsed | 5114 |\n", + "| total_timesteps | 2592000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.37 |\n", + "| explained_variance | 0.952 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 80999 |\n", + "| policy_loss | -0.0155 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.000884 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 959 |\n", + "| ep_rew_mean | 663 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 81100 |\n", + "| time_elapsed | 5120 |\n", + "| total_timesteps | 2595200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.15 |\n", + "| explained_variance | 0.98 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 81099 |\n", + "| policy_loss | -0.00625 |\n", + "| std | 0.0461 |\n", + "| value_loss | 0.00112 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 959 |\n", + "| ep_rew_mean | 670 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 81200 |\n", + "| time_elapsed | 5125 |\n", + "| total_timesteps | 2598400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.14 |\n", + "| explained_variance | 0.95 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 81199 |\n", + "| policy_loss | -0.0128 |\n", + "| std | 0.0461 |\n", + "| value_loss | 0.00276 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 959 |\n", + "| ep_rew_mean | 679 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 81300 |\n", + "| time_elapsed | 5133 |\n", + "| total_timesteps | 2601600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.35 |\n", + "| explained_variance | 0.989 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 81299 |\n", + "| policy_loss | 0.0192 |\n", + "| std | 0.0463 |\n", + "| value_loss | 0.000611 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 959 |\n", + "| ep_rew_mean | 685 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 81400 |\n", + "| time_elapsed | 5138 |\n", + "| total_timesteps | 2604800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.23 |\n", + "| explained_variance | 0.735 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 81399 |\n", + "| policy_loss | 0.0125 |\n", + "| std | 0.0463 |\n", + "| value_loss | 0.00224 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 968 |\n", + "| ep_rew_mean | 702 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 81500 |\n", + "| time_elapsed | 5145 |\n", + "| total_timesteps | 2608000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.5 |\n", + "| explained_variance | 0.981 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 81499 |\n", + "| policy_loss | -0.0797 |\n", + "| std | 0.0461 |\n", + "| value_loss | 0.00138 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 968 |\n", + "| ep_rew_mean | 710 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 81600 |\n", + "| time_elapsed | 5151 |\n", + "| total_timesteps | 2611200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.18 |\n", + "| explained_variance | 0.984 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 81599 |\n", + "| policy_loss | -0.04 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.00197 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 968 |\n", + "| ep_rew_mean | 714 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 81700 |\n", + "| time_elapsed | 5160 |\n", + "| total_timesteps | 2614400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.2 |\n", + "| explained_variance | 0.938 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 81699 |\n", + "| policy_loss | -0.00158 |\n", + "| std | 0.0457 |\n", + "| value_loss | 0.00122 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 968 |\n", + "| ep_rew_mean | 717 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 81800 |\n", + "| time_elapsed | 5167 |\n", + "| total_timesteps | 2617600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.44 |\n", + "| explained_variance | 0.654 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 81799 |\n", + "| policy_loss | 0.0663 |\n", + "| std | 0.0457 |\n", + "| value_loss | 0.00115 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 975 |\n", + "| ep_rew_mean | 724 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 81900 |\n", + "| time_elapsed | 5172 |\n", + "| total_timesteps | 2620800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.41 |\n", + "| explained_variance | 0.921 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 81899 |\n", + "| policy_loss | -0.0971 |\n", + "| std | 0.0456 |\n", + "| value_loss | 0.00506 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 975 |\n", + "| ep_rew_mean | 727 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 82000 |\n", + "| time_elapsed | 5180 |\n", + "| total_timesteps | 2624000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.47 |\n", + "| explained_variance | 0.968 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 81999 |\n", + "| policy_loss | 0.00015 |\n", + "| std | 0.0458 |\n", + "| value_loss | 0.00118 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 975 |\n", + "| ep_rew_mean | 728 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 82100 |\n", + "| time_elapsed | 5185 |\n", + "| total_timesteps | 2627200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.32 |\n", + "| explained_variance | 0.951 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 82099 |\n", + "| policy_loss | -0.0469 |\n", + "| std | 0.0461 |\n", + "| value_loss | 0.00302 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 975 |\n", + "| ep_rew_mean | 728 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 82200 |\n", + "| time_elapsed | 5191 |\n", + "| total_timesteps | 2630400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.26 |\n", + "| explained_variance | 0.986 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 82199 |\n", + "| policy_loss | 0.0199 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.00141 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 975 |\n", + "| ep_rew_mean | 733 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 82300 |\n", + "| time_elapsed | 5198 |\n", + "| total_timesteps | 2633600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.46 |\n", + "| explained_variance | 0.888 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 82299 |\n", + "| policy_loss | 0.0146 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.00194 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 975 |\n", + "| ep_rew_mean | 736 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 82400 |\n", + "| time_elapsed | 5203 |\n", + "| total_timesteps | 2636800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.09 |\n", + "| explained_variance | 0.998 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 82399 |\n", + "| policy_loss | 0.00343 |\n", + "| std | 0.0459 |\n", + "| value_loss | 0.000222 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 975 |\n", + "| ep_rew_mean | 749 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 82500 |\n", + "| time_elapsed | 5211 |\n", + "| total_timesteps | 2640000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.49 |\n", + "| explained_variance | 0.925 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 82499 |\n", + "| policy_loss | 0.0305 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.000452 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 975 |\n", + "| ep_rew_mean | 764 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 82600 |\n", + "| time_elapsed | 5217 |\n", + "| total_timesteps | 2643200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.04 |\n", + "| explained_variance | 0.979 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 82599 |\n", + "| policy_loss | -0.00615 |\n", + "| std | 0.0458 |\n", + "| value_loss | 0.00259 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 975 |\n", + "| ep_rew_mean | 770 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 82700 |\n", + "| time_elapsed | 5223 |\n", + "| total_timesteps | 2646400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.25 |\n", + "| explained_variance | 0.996 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 82699 |\n", + "| policy_loss | 0.0569 |\n", + "| std | 0.0458 |\n", + "| value_loss | 0.00166 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 975 |\n", + "| ep_rew_mean | 777 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 82800 |\n", + "| time_elapsed | 5232 |\n", + "| total_timesteps | 2649600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.33 |\n", + "| explained_variance | 0.966 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 82799 |\n", + "| policy_loss | -0.0905 |\n", + "| std | 0.0459 |\n", + "| value_loss | 0.00782 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 975 |\n", + "| ep_rew_mean | 780 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 82900 |\n", + "| time_elapsed | 5237 |\n", + "| total_timesteps | 2652800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.53 |\n", + "| explained_variance | 0.996 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 82899 |\n", + "| policy_loss | 0.0512 |\n", + "| std | 0.0458 |\n", + "| value_loss | 0.00155 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 975 |\n", + "| ep_rew_mean | 780 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 83000 |\n", + "| time_elapsed | 5244 |\n", + "| total_timesteps | 2656000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.83 |\n", + "| explained_variance | 0.88 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 82999 |\n", + "| policy_loss | 4.99e-05 |\n", + "| std | 0.0456 |\n", + "| value_loss | 0.000611 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 975 |\n", + "| ep_rew_mean | 781 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 83100 |\n", + "| time_elapsed | 5250 |\n", + "| total_timesteps | 2659200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.36 |\n", + "| explained_variance | 0.996 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 83099 |\n", + "| policy_loss | 0.00422 |\n", + "| std | 0.0457 |\n", + "| value_loss | 0.00108 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 983 |\n", + "| ep_rew_mean | 782 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 83200 |\n", + "| time_elapsed | 5256 |\n", + "| total_timesteps | 2662400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.2 |\n", + "| explained_variance | 0.991 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 83199 |\n", + "| policy_loss | 0.0296 |\n", + "| std | 0.0459 |\n", + "| value_loss | 0.00421 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 991 |\n", + "| ep_rew_mean | 790 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 83300 |\n", + "| time_elapsed | 5263 |\n", + "| total_timesteps | 2665600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.21 |\n", + "| explained_variance | 0.999 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 83299 |\n", + "| policy_loss | -0.00589 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.000247 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 800 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 83400 |\n", + "| time_elapsed | 5269 |\n", + "| total_timesteps | 2668800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.32 |\n", + "| explained_variance | 0.997 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 83399 |\n", + "| policy_loss | 0.0144 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.00047 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 808 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 83500 |\n", + "| time_elapsed | 5278 |\n", + "| total_timesteps | 2672000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.63 |\n", + "| explained_variance | 0.975 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 83499 |\n", + "| policy_loss | 0.0669 |\n", + "| std | 0.0459 |\n", + "| value_loss | 0.00132 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 814 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 83600 |\n", + "| time_elapsed | 5284 |\n", + "| total_timesteps | 2675200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.56 |\n", + "| explained_variance | 0.978 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 83599 |\n", + "| policy_loss | -0.0149 |\n", + "| std | 0.0461 |\n", + "| value_loss | 0.00345 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 823 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 83700 |\n", + "| time_elapsed | 5289 |\n", + "| total_timesteps | 2678400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.34 |\n", + "| explained_variance | 0.995 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 83699 |\n", + "| policy_loss | -0.082 |\n", + "| std | 0.0458 |\n", + "| value_loss | 0.00315 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 828 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 83800 |\n", + "| time_elapsed | 5299 |\n", + "| total_timesteps | 2681600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.3 |\n", + "| explained_variance | 0.876 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 83799 |\n", + "| policy_loss | 0.117 |\n", + "| std | 0.0457 |\n", + "| value_loss | 0.0079 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 832 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 83900 |\n", + "| time_elapsed | 5305 |\n", + "| total_timesteps | 2684800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.57 |\n", + "| explained_variance | 0.831 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 83899 |\n", + "| policy_loss | 0.0369 |\n", + "| std | 0.0459 |\n", + "| value_loss | 0.00323 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 844 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 84000 |\n", + "| time_elapsed | 5310 |\n", + "| total_timesteps | 2688000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.57 |\n", + "| explained_variance | -1.31 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 83999 |\n", + "| policy_loss | 0.0555 |\n", + "| std | 0.0458 |\n", + "| value_loss | 0.0123 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 851 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 84100 |\n", + "| time_elapsed | 5318 |\n", + "| total_timesteps | 2691200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.38 |\n", + "| explained_variance | 0.984 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 84099 |\n", + "| policy_loss | -0.0144 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.00335 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 987 |\n", + "| ep_rew_mean | 844 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 84200 |\n", + "| time_elapsed | 5323 |\n", + "| total_timesteps | 2694400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.37 |\n", + "| explained_variance | 0.967 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 84199 |\n", + "| policy_loss | -0.0498 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.0044 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 987 |\n", + "| ep_rew_mean | 846 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 84300 |\n", + "| time_elapsed | 5330 |\n", + "| total_timesteps | 2697600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.52 |\n", + "| explained_variance | 0.967 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 84299 |\n", + "| policy_loss | 0.0197 |\n", + "| std | 0.0461 |\n", + "| value_loss | 0.0045 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 987 |\n", + "| ep_rew_mean | 847 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 84400 |\n", + "| time_elapsed | 5336 |\n", + "| total_timesteps | 2700800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.35 |\n", + "| explained_variance | 0.797 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 84399 |\n", + "| policy_loss | 0.0167 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.0208 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 987 |\n", + "| ep_rew_mean | 831 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 84500 |\n", + "| time_elapsed | 5342 |\n", + "| total_timesteps | 2704000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.57 |\n", + "| explained_variance | 0.984 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 84499 |\n", + "| policy_loss | -0.151 |\n", + "| std | 0.0462 |\n", + "| value_loss | 0.00494 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 979 |\n", + "| ep_rew_mean | 826 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 84600 |\n", + "| time_elapsed | 5349 |\n", + "| total_timesteps | 2707200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.19 |\n", + "| explained_variance | 0.999 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 84599 |\n", + "| policy_loss | 0.00876 |\n", + "| std | 0.0463 |\n", + "| value_loss | 0.000718 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 979 |\n", + "| ep_rew_mean | 817 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 84700 |\n", + "| time_elapsed | 5355 |\n", + "| total_timesteps | 2710400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.3 |\n", + "| explained_variance | 0.866 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 84699 |\n", + "| policy_loss | -0.127 |\n", + "| std | 0.0459 |\n", + "| value_loss | 0.00475 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 979 |\n", + "| ep_rew_mean | 815 |\n", + "| time/ | |\n", + "| fps | 506 |\n", + "| iterations | 84800 |\n", + "| time_elapsed | 5362 |\n", + "| total_timesteps | 2713600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.33 |\n", + "| explained_variance | 0.985 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 84799 |\n", + "| policy_loss | -0.0317 |\n", + "| std | 0.0461 |\n", + "| value_loss | 0.00304 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 979 |\n", + "| ep_rew_mean | 813 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 84900 |\n", + "| time_elapsed | 5370 |\n", + "| total_timesteps | 2716800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.48 |\n", + "| explained_variance | 0.977 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 84899 |\n", + "| policy_loss | -0.13 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.0041 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 979 |\n", + "| ep_rew_mean | 812 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 85000 |\n", + "| time_elapsed | 5375 |\n", + "| total_timesteps | 2720000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.35 |\n", + "| explained_variance | 0.985 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 84999 |\n", + "| policy_loss | 0.0279 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.00375 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 972 |\n", + "| ep_rew_mean | 808 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 85100 |\n", + "| time_elapsed | 5383 |\n", + "| total_timesteps | 2723200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.31 |\n", + "| explained_variance | 0.959 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 85099 |\n", + "| policy_loss | 0.0366 |\n", + "| std | 0.0457 |\n", + "| value_loss | 0.00159 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 963 |\n", + "| ep_rew_mean | 813 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 85200 |\n", + "| time_elapsed | 5388 |\n", + "| total_timesteps | 2726400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.19 |\n", + "| explained_variance | 0.908 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 85199 |\n", + "| policy_loss | 0.0465 |\n", + "| std | 0.0458 |\n", + "| value_loss | 0.0041 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 963 |\n", + "| ep_rew_mean | 814 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 85300 |\n", + "| time_elapsed | 5395 |\n", + "| total_timesteps | 2729600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.23 |\n", + "| explained_variance | 0.972 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 85299 |\n", + "| policy_loss | -0.0234 |\n", + "| std | 0.0459 |\n", + "| value_loss | 0.00671 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 963 |\n", + "| ep_rew_mean | 818 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 85400 |\n", + "| time_elapsed | 5401 |\n", + "| total_timesteps | 2732800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.32 |\n", + "| explained_variance | 0.987 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 85399 |\n", + "| policy_loss | 0.0138 |\n", + "| std | 0.0461 |\n", + "| value_loss | 0.00312 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 963 |\n", + "| ep_rew_mean | 816 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 85500 |\n", + "| time_elapsed | 5407 |\n", + "| total_timesteps | 2736000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.3 |\n", + "| explained_variance | 0.803 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 85499 |\n", + "| policy_loss | -0.00148 |\n", + "| std | 0.0461 |\n", + "| value_loss | 0.0131 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 963 |\n", + "| ep_rew_mean | 813 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 85600 |\n", + "| time_elapsed | 5414 |\n", + "| total_timesteps | 2739200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.27 |\n", + "| explained_variance | 0.989 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 85599 |\n", + "| policy_loss | -0.038 |\n", + "| std | 0.0462 |\n", + "| value_loss | 0.00286 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 963 |\n", + "| ep_rew_mean | 809 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 85700 |\n", + "| time_elapsed | 5420 |\n", + "| total_timesteps | 2742400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.35 |\n", + "| explained_variance | 0.981 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 85699 |\n", + "| policy_loss | -0.0368 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.00252 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 963 |\n", + "| ep_rew_mean | 809 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 85800 |\n", + "| time_elapsed | 5427 |\n", + "| total_timesteps | 2745600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.5 |\n", + "| explained_variance | 0.983 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 85799 |\n", + "| policy_loss | -0.158 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.00493 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 963 |\n", + "| ep_rew_mean | 812 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 85900 |\n", + "| time_elapsed | 5434 |\n", + "| total_timesteps | 2748800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.6 |\n", + "| explained_variance | 0.98 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 85899 |\n", + "| policy_loss | 0.045 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.0021 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 963 |\n", + "| ep_rew_mean | 824 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 86000 |\n", + "| time_elapsed | 5441 |\n", + "| total_timesteps | 2752000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.47 |\n", + "| explained_variance | 0.997 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 85999 |\n", + "| policy_loss | -0.0604 |\n", + "| std | 0.046 |\n", + "| value_loss | 0.00368 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 963 |\n", + "| ep_rew_mean | 825 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 86100 |\n", + "| time_elapsed | 5448 |\n", + "| total_timesteps | 2755200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.5 |\n", + "| explained_variance | 0.997 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 86099 |\n", + "| policy_loss | 0.00828 |\n", + "| std | 0.0458 |\n", + "| value_loss | 0.000604 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 963 |\n", + "| ep_rew_mean | 842 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 86200 |\n", + "| time_elapsed | 5453 |\n", + "| total_timesteps | 2758400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.41 |\n", + "| explained_variance | 0.892 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 86199 |\n", + "| policy_loss | 0.195 |\n", + "| std | 0.0458 |\n", + "| value_loss | 0.00897 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 963 |\n", + "| ep_rew_mean | 841 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 86300 |\n", + "| time_elapsed | 5461 |\n", + "| total_timesteps | 2761600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.45 |\n", + "| explained_variance | 0.997 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 86299 |\n", + "| policy_loss | -0.0102 |\n", + "| std | 0.0456 |\n", + "| value_loss | 0.0025 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 955 |\n", + "| ep_rew_mean | 835 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 86400 |\n", + "| time_elapsed | 5466 |\n", + "| total_timesteps | 2764800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.45 |\n", + "| explained_variance | 0.974 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 86399 |\n", + "| policy_loss | 0.0365 |\n", + "| std | 0.0455 |\n", + "| value_loss | 0.00368 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 955 |\n", + "| ep_rew_mean | 840 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 86500 |\n", + "| time_elapsed | 5473 |\n", + "| total_timesteps | 2768000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.54 |\n", + "| explained_variance | 0.986 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 86499 |\n", + "| policy_loss | -0.0353 |\n", + "| std | 0.0454 |\n", + "| value_loss | 0.00285 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 946 |\n", + "| ep_rew_mean | 835 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 86600 |\n", + "| time_elapsed | 5479 |\n", + "| total_timesteps | 2771200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.31 |\n", + "| explained_variance | 0.993 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 86599 |\n", + "| policy_loss | 0.0261 |\n", + "| std | 0.0456 |\n", + "| value_loss | 0.00064 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 946 |\n", + "| ep_rew_mean | 831 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 86700 |\n", + "| time_elapsed | 5484 |\n", + "| total_timesteps | 2774400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.44 |\n", + "| explained_variance | 0.903 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 86699 |\n", + "| policy_loss | 0.124 |\n", + "| std | 0.0455 |\n", + "| value_loss | 0.00328 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 946 |\n", + "| ep_rew_mean | 825 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 86800 |\n", + "| time_elapsed | 5492 |\n", + "| total_timesteps | 2777600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.42 |\n", + "| explained_variance | 0.996 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 86799 |\n", + "| policy_loss | 0.00271 |\n", + "| std | 0.0458 |\n", + "| value_loss | 0.00081 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 946 |\n", + "| ep_rew_mean | 818 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 86900 |\n", + "| time_elapsed | 5497 |\n", + "| total_timesteps | 2780800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.34 |\n", + "| explained_variance | 0.993 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 86899 |\n", + "| policy_loss | 0.0514 |\n", + "| std | 0.0456 |\n", + "| value_loss | 0.000644 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 946 |\n", + "| ep_rew_mean | 814 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 87000 |\n", + "| time_elapsed | 5503 |\n", + "| total_timesteps | 2784000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.35 |\n", + "| explained_variance | 0.917 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 86999 |\n", + "| policy_loss | -0.0317 |\n", + "| std | 0.0456 |\n", + "| value_loss | 0.00273 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 954 |\n", + "| ep_rew_mean | 820 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 87100 |\n", + "| time_elapsed | 5512 |\n", + "| total_timesteps | 2787200 |\n", + "| train/ | |\n", + "| entropy_loss | -2 |\n", + "| explained_variance | 0.246 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 87099 |\n", + "| policy_loss | 0.0666 |\n", + "| std | 0.0457 |\n", + "| value_loss | 0.00578 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 959 |\n", + "| ep_rew_mean | 827 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 87200 |\n", + "| time_elapsed | 5517 |\n", + "| total_timesteps | 2790400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.42 |\n", + "| explained_variance | 0.98 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 87199 |\n", + "| policy_loss | -0.115 |\n", + "| std | 0.0458 |\n", + "| value_loss | 0.00508 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 959 |\n", + "| ep_rew_mean | 829 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 87300 |\n", + "| time_elapsed | 5525 |\n", + "| total_timesteps | 2793600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.31 |\n", + "| explained_variance | 0.972 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 87299 |\n", + "| policy_loss | -0.0507 |\n", + "| std | 0.0458 |\n", + "| value_loss | 0.00675 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 959 |\n", + "| ep_rew_mean | 829 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 87400 |\n", + "| time_elapsed | 5530 |\n", + "| total_timesteps | 2796800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.6 |\n", + "| explained_variance | 0.981 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 87399 |\n", + "| policy_loss | -0.00794 |\n", + "| std | 0.0458 |\n", + "| value_loss | 0.000538 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 959 |\n", + "| ep_rew_mean | 842 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 87500 |\n", + "| time_elapsed | 5536 |\n", + "| total_timesteps | 2800000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.22 |\n", + "| explained_variance | 0.995 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 87499 |\n", + "| policy_loss | -0.0881 |\n", + "| std | 0.0458 |\n", + "| value_loss | 0.0018 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 967 |\n", + "| ep_rew_mean | 859 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 87600 |\n", + "| time_elapsed | 5543 |\n", + "| total_timesteps | 2803200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.38 |\n", + "| explained_variance | 0.946 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 87599 |\n", + "| policy_loss | 0.12 |\n", + "| std | 0.0457 |\n", + "| value_loss | 0.00322 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 967 |\n", + "| ep_rew_mean | 878 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 87700 |\n", + "| time_elapsed | 5549 |\n", + "| total_timesteps | 2806400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.39 |\n", + "| explained_variance | 0.996 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 87699 |\n", + "| policy_loss | 0.0364 |\n", + "| std | 0.0455 |\n", + "| value_loss | 0.00123 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 967 |\n", + "| ep_rew_mean | 885 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 87800 |\n", + "| time_elapsed | 5558 |\n", + "| total_timesteps | 2809600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.28 |\n", + "| explained_variance | 0.939 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 87799 |\n", + "| policy_loss | 0.0629 |\n", + "| std | 0.0456 |\n", + "| value_loss | 0.00391 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 967 |\n", + "| ep_rew_mean | 885 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 87900 |\n", + "| time_elapsed | 5564 |\n", + "| total_timesteps | 2812800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.16 |\n", + "| explained_variance | 0.997 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 87899 |\n", + "| policy_loss | -0.0275 |\n", + "| std | 0.0457 |\n", + "| value_loss | 0.000823 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 967 |\n", + "| ep_rew_mean | 890 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 88000 |\n", + "| time_elapsed | 5570 |\n", + "| total_timesteps | 2816000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.2 |\n", + "| explained_variance | 0.954 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 87999 |\n", + "| policy_loss | 0.0103 |\n", + "| std | 0.0455 |\n", + "| value_loss | 0.00163 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 974 |\n", + "| ep_rew_mean | 904 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 88100 |\n", + "| time_elapsed | 5578 |\n", + "| total_timesteps | 2819200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.28 |\n", + "| explained_variance | 0.762 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 88099 |\n", + "| policy_loss | 0.0709 |\n", + "| std | 0.0457 |\n", + "| value_loss | 0.00434 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 974 |\n", + "| ep_rew_mean | 912 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 88200 |\n", + "| time_elapsed | 5584 |\n", + "| total_timesteps | 2822400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.34 |\n", + "| explained_variance | 0.968 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 88199 |\n", + "| policy_loss | -0.0723 |\n", + "| std | 0.0456 |\n", + "| value_loss | 0.00395 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 983 |\n", + "| ep_rew_mean | 928 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 88300 |\n", + "| time_elapsed | 5592 |\n", + "| total_timesteps | 2825600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.38 |\n", + "| explained_variance | 0.961 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 88299 |\n", + "| policy_loss | 0.018 |\n", + "| std | 0.0457 |\n", + "| value_loss | 0.00106 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 983 |\n", + "| ep_rew_mean | 929 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 88400 |\n", + "| time_elapsed | 5597 |\n", + "| total_timesteps | 2828800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.32 |\n", + "| explained_variance | 0.977 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 88399 |\n", + "| policy_loss | -0.0332 |\n", + "| std | 0.0456 |\n", + "| value_loss | 0.00395 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 983 |\n", + "| ep_rew_mean | 938 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 88500 |\n", + "| time_elapsed | 5604 |\n", + "| total_timesteps | 2832000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.51 |\n", + "| explained_variance | 0.995 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 88499 |\n", + "| policy_loss | -0.0108 |\n", + "| std | 0.0456 |\n", + "| value_loss | 0.000429 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 983 |\n", + "| ep_rew_mean | 943 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 88600 |\n", + "| time_elapsed | 5610 |\n", + "| total_timesteps | 2835200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.51 |\n", + "| explained_variance | 0.346 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 88599 |\n", + "| policy_loss | -0.0781 |\n", + "| std | 0.0455 |\n", + "| value_loss | 0.00428 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 983 |\n", + "| ep_rew_mean | 956 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 88700 |\n", + "| time_elapsed | 5616 |\n", + "| total_timesteps | 2838400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.37 |\n", + "| explained_variance | 0.998 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 88699 |\n", + "| policy_loss | -0.0178 |\n", + "| std | 0.0457 |\n", + "| value_loss | 0.000451 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 983 |\n", + "| ep_rew_mean | 967 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 88800 |\n", + "| time_elapsed | 5623 |\n", + "| total_timesteps | 2841600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.4 |\n", + "| explained_variance | 0.989 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 88799 |\n", + "| policy_loss | 0.112 |\n", + "| std | 0.0457 |\n", + "| value_loss | 0.0015 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 983 |\n", + "| ep_rew_mean | 970 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 88900 |\n", + "| time_elapsed | 5628 |\n", + "| total_timesteps | 2844800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.57 |\n", + "| explained_variance | 0.992 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 88899 |\n", + "| policy_loss | 0.153 |\n", + "| std | 0.0455 |\n", + "| value_loss | 0.00208 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 983 |\n", + "| ep_rew_mean | 975 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 89000 |\n", + "| time_elapsed | 5635 |\n", + "| total_timesteps | 2848000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.2 |\n", + "| explained_variance | 0.988 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 88999 |\n", + "| policy_loss | -0.0193 |\n", + "| std | 0.0457 |\n", + "| value_loss | 0.00103 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 983 |\n", + "| ep_rew_mean | 976 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 89100 |\n", + "| time_elapsed | 5641 |\n", + "| total_timesteps | 2851200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.53 |\n", + "| explained_variance | 0.985 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 89099 |\n", + "| policy_loss | 0.0608 |\n", + "| std | 0.0455 |\n", + "| value_loss | 0.00206 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 983 |\n", + "| ep_rew_mean | 972 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 89200 |\n", + "| time_elapsed | 5648 |\n", + "| total_timesteps | 2854400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.29 |\n", + "| explained_variance | 0.927 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 89199 |\n", + "| policy_loss | 0.0164 |\n", + "| std | 0.0453 |\n", + "| value_loss | 0.00159 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 983 |\n", + "| ep_rew_mean | 972 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 89300 |\n", + "| time_elapsed | 5656 |\n", + "| total_timesteps | 2857600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.55 |\n", + "| explained_variance | 0.952 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 89299 |\n", + "| policy_loss | -0.0196 |\n", + "| std | 0.0452 |\n", + "| value_loss | 0.00075 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 983 |\n", + "| ep_rew_mean | 975 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 89400 |\n", + "| time_elapsed | 5662 |\n", + "| total_timesteps | 2860800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.35 |\n", + "| explained_variance | 0.948 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 89399 |\n", + "| policy_loss | -0.0291 |\n", + "| std | 0.0453 |\n", + "| value_loss | 0.00151 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 991 |\n", + "| ep_rew_mean | 984 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 89500 |\n", + "| time_elapsed | 5669 |\n", + "| total_timesteps | 2864000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.29 |\n", + "| explained_variance | 0.993 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 89499 |\n", + "| policy_loss | 0.0812 |\n", + "| std | 0.0452 |\n", + "| value_loss | 0.00255 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 991 |\n", + "| ep_rew_mean | 987 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 89600 |\n", + "| time_elapsed | 5675 |\n", + "| total_timesteps | 2867200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.31 |\n", + "| explained_variance | 0.939 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 89599 |\n", + "| policy_loss | 0.0198 |\n", + "| std | 0.0454 |\n", + "| value_loss | 0.00282 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 997 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 89700 |\n", + "| time_elapsed | 5680 |\n", + "| total_timesteps | 2870400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.23 |\n", + "| explained_variance | 0.987 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 89699 |\n", + "| policy_loss | -0.00737 |\n", + "| std | 0.0455 |\n", + "| value_loss | 0.00201 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 998 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 89800 |\n", + "| time_elapsed | 5688 |\n", + "| total_timesteps | 2873600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.28 |\n", + "| explained_variance | 0.963 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 89799 |\n", + "| policy_loss | -0.0463 |\n", + "| std | 0.0453 |\n", + "| value_loss | 0.00593 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 1e+03 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 89900 |\n", + "| time_elapsed | 5693 |\n", + "| total_timesteps | 2876800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.4 |\n", + "| explained_variance | 0.989 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 89899 |\n", + "| policy_loss | 0.02 |\n", + "| std | 0.0455 |\n", + "| value_loss | 0.000768 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 1.01e+03 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 90000 |\n", + "| time_elapsed | 5700 |\n", + "| total_timesteps | 2880000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.17 |\n", + "| explained_variance | 0.71 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 89999 |\n", + "| policy_loss | -0.0764 |\n", + "| std | 0.0454 |\n", + "| value_loss | 0.00112 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 1.01e+03 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 90100 |\n", + "| time_elapsed | 5706 |\n", + "| total_timesteps | 2883200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.18 |\n", + "| explained_variance | 0.948 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 90099 |\n", + "| policy_loss | -0.0403 |\n", + "| std | 0.0453 |\n", + "| value_loss | 0.000938 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 1.01e+03 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 90200 |\n", + "| time_elapsed | 5712 |\n", + "| total_timesteps | 2886400 |\n", + "| train/ | |\n", + "| entropy_loss | -1.88 |\n", + "| explained_variance | 0.983 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 90199 |\n", + "| policy_loss | 0.0222 |\n", + "| std | 0.0452 |\n", + "| value_loss | 0.000431 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 1e+03 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 90300 |\n", + "| time_elapsed | 5721 |\n", + "| total_timesteps | 2889600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.33 |\n", + "| explained_variance | 0.993 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 90299 |\n", + "| policy_loss | -0.0326 |\n", + "| std | 0.0451 |\n", + "| value_loss | 0.00105 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 1e+03 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 90400 |\n", + "| time_elapsed | 5727 |\n", + "| total_timesteps | 2892800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.19 |\n", + "| explained_variance | 0.882 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 90399 |\n", + "| policy_loss | -0.0492 |\n", + "| std | 0.0452 |\n", + "| value_loss | 0.00534 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 994 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 90500 |\n", + "| time_elapsed | 5734 |\n", + "| total_timesteps | 2896000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.86 |\n", + "| explained_variance | 0.983 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 90499 |\n", + "| policy_loss | 0.00698 |\n", + "| std | 0.0452 |\n", + "| value_loss | 0.000371 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 982 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 90600 |\n", + "| time_elapsed | 5739 |\n", + "| total_timesteps | 2899200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.17 |\n", + "| explained_variance | 0.977 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 90599 |\n", + "| policy_loss | 0.0885 |\n", + "| std | 0.0451 |\n", + "| value_loss | 0.00214 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 976 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 90700 |\n", + "| time_elapsed | 5746 |\n", + "| total_timesteps | 2902400 |\n", + "| train/ | |\n", + "| entropy_loss | -1.97 |\n", + "| explained_variance | 0.989 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 90699 |\n", + "| policy_loss | 0.023 |\n", + "| std | 0.0452 |\n", + "| value_loss | 0.000723 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 968 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 90800 |\n", + "| time_elapsed | 5753 |\n", + "| total_timesteps | 2905600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.37 |\n", + "| explained_variance | 0.992 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 90799 |\n", + "| policy_loss | 0.0512 |\n", + "| std | 0.0453 |\n", + "| value_loss | 0.00229 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 966 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 90900 |\n", + "| time_elapsed | 5758 |\n", + "| total_timesteps | 2908800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.05 |\n", + "| explained_variance | 0.987 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 90899 |\n", + "| policy_loss | -0.0913 |\n", + "| std | 0.0453 |\n", + "| value_loss | 0.00713 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 951 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 91000 |\n", + "| time_elapsed | 5765 |\n", + "| total_timesteps | 2912000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.69 |\n", + "| explained_variance | 0.998 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 90999 |\n", + "| policy_loss | -0.0383 |\n", + "| std | 0.0452 |\n", + "| value_loss | 0.0011 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 941 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 91100 |\n", + "| time_elapsed | 5771 |\n", + "| total_timesteps | 2915200 |\n", + "| train/ | |\n", + "| entropy_loss | -1.78 |\n", + "| explained_variance | 0.994 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 91099 |\n", + "| policy_loss | -0.0482 |\n", + "| std | 0.0451 |\n", + "| value_loss | 0.000924 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 934 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 91200 |\n", + "| time_elapsed | 5777 |\n", + "| total_timesteps | 2918400 |\n", + "| train/ | |\n", + "| entropy_loss | -1.92 |\n", + "| explained_variance | 0.982 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 91199 |\n", + "| policy_loss | -0.0108 |\n", + "| std | 0.0452 |\n", + "| value_loss | 0.00202 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 930 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 91300 |\n", + "| time_elapsed | 5783 |\n", + "| total_timesteps | 2921600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.18 |\n", + "| explained_variance | 0.994 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 91299 |\n", + "| policy_loss | -0.0333 |\n", + "| std | 0.0452 |\n", + "| value_loss | 0.00167 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 928 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 91400 |\n", + "| time_elapsed | 5790 |\n", + "| total_timesteps | 2924800 |\n", + "| train/ | |\n", + "| entropy_loss | -0.918 |\n", + "| explained_variance | 0.999 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 91399 |\n", + "| policy_loss | 0.00323 |\n", + "| std | 0.0451 |\n", + "| value_loss | 0.000211 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 919 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 91500 |\n", + "| time_elapsed | 5799 |\n", + "| total_timesteps | 2928000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.59 |\n", + "| explained_variance | 0.989 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 91499 |\n", + "| policy_loss | -0.013 |\n", + "| std | 0.0451 |\n", + "| value_loss | 0.00119 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 917 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 91600 |\n", + "| time_elapsed | 5804 |\n", + "| total_timesteps | 2931200 |\n", + "| train/ | |\n", + "| entropy_loss | -1.85 |\n", + "| explained_variance | 0.989 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 91599 |\n", + "| policy_loss | -0.0168 |\n", + "| std | 0.0451 |\n", + "| value_loss | 0.000953 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 914 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 91700 |\n", + "| time_elapsed | 5811 |\n", + "| total_timesteps | 2934400 |\n", + "| train/ | |\n", + "| entropy_loss | -1.82 |\n", + "| explained_variance | 0.998 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 91699 |\n", + "| policy_loss | 0.0209 |\n", + "| std | 0.0451 |\n", + "| value_loss | 0.000876 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 911 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 91800 |\n", + "| time_elapsed | 5817 |\n", + "| total_timesteps | 2937600 |\n", + "| train/ | |\n", + "| entropy_loss | -1.9 |\n", + "| explained_variance | 0.941 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 91799 |\n", + "| policy_loss | 0.0572 |\n", + "| std | 0.0451 |\n", + "| value_loss | 0.00416 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 909 |\n", + "| time/ | |\n", + "| fps | 505 |\n", + "| iterations | 91900 |\n", + "| time_elapsed | 5822 |\n", + "| total_timesteps | 2940800 |\n", + "| train/ | |\n", + "| entropy_loss | -1.69 |\n", + "| explained_variance | 0.997 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 91899 |\n", + "| policy_loss | -0.000509 |\n", + "| std | 0.0452 |\n", + "| value_loss | 0.00194 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 893 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 92000 |\n", + "| time_elapsed | 5830 |\n", + "| total_timesteps | 2944000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.73 |\n", + "| explained_variance | 0.968 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 91999 |\n", + "| policy_loss | 0.0288 |\n", + "| std | 0.0452 |\n", + "| value_loss | 0.00279 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 886 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 92100 |\n", + "| time_elapsed | 5837 |\n", + "| total_timesteps | 2947200 |\n", + "| train/ | |\n", + "| entropy_loss | -1.7 |\n", + "| explained_variance | 1 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 92099 |\n", + "| policy_loss | -0.00292 |\n", + "| std | 0.045 |\n", + "| value_loss | 0.000208 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 879 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 92200 |\n", + "| time_elapsed | 5844 |\n", + "| total_timesteps | 2950400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.09 |\n", + "| explained_variance | 0.991 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 92199 |\n", + "| policy_loss | 0.00187 |\n", + "| std | 0.0452 |\n", + "| value_loss | 0.00145 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 883 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 92300 |\n", + "| time_elapsed | 5850 |\n", + "| total_timesteps | 2953600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.02 |\n", + "| explained_variance | 0.993 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 92299 |\n", + "| policy_loss | 0.0321 |\n", + "| std | 0.0452 |\n", + "| value_loss | 0.000984 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 882 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 92400 |\n", + "| time_elapsed | 5856 |\n", + "| total_timesteps | 2956800 |\n", + "| train/ | |\n", + "| entropy_loss | -1.84 |\n", + "| explained_variance | 0.991 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 92399 |\n", + "| policy_loss | -0.0172 |\n", + "| std | 0.0452 |\n", + "| value_loss | 0.00167 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 886 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 92500 |\n", + "| time_elapsed | 5865 |\n", + "| total_timesteps | 2960000 |\n", + "| train/ | |\n", + "| entropy_loss | -2.04 |\n", + "| explained_variance | 0.992 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 92499 |\n", + "| policy_loss | -0.00194 |\n", + "| std | 0.0454 |\n", + "| value_loss | 0.000335 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 893 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 92600 |\n", + "| time_elapsed | 5870 |\n", + "| total_timesteps | 2963200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.17 |\n", + "| explained_variance | 0.598 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 92599 |\n", + "| policy_loss | -0.0165 |\n", + "| std | 0.0453 |\n", + "| value_loss | 0.000878 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 898 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 92700 |\n", + "| time_elapsed | 5877 |\n", + "| total_timesteps | 2966400 |\n", + "| train/ | |\n", + "| entropy_loss | -2.04 |\n", + "| explained_variance | 0.998 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 92699 |\n", + "| policy_loss | 0.0342 |\n", + "| std | 0.0451 |\n", + "| value_loss | 0.000669 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 903 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 92800 |\n", + "| time_elapsed | 5883 |\n", + "| total_timesteps | 2969600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.19 |\n", + "| explained_variance | 0.983 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 92799 |\n", + "| policy_loss | 0.0194 |\n", + "| std | 0.0453 |\n", + "| value_loss | 0.000898 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 907 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 92900 |\n", + "| time_elapsed | 5889 |\n", + "| total_timesteps | 2972800 |\n", + "| train/ | |\n", + "| entropy_loss | -1.68 |\n", + "| explained_variance | 0.996 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 92899 |\n", + "| policy_loss | 0.00115 |\n", + "| std | 0.0453 |\n", + "| value_loss | 0.00192 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 914 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 93000 |\n", + "| time_elapsed | 5895 |\n", + "| total_timesteps | 2976000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.96 |\n", + "| explained_variance | 0.999 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 92999 |\n", + "| policy_loss | -0.0135 |\n", + "| std | 0.0453 |\n", + "| value_loss | 0.000344 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 915 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 93100 |\n", + "| time_elapsed | 5901 |\n", + "| total_timesteps | 2979200 |\n", + "| train/ | |\n", + "| entropy_loss | -1.91 |\n", + "| explained_variance | 0.97 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 93099 |\n", + "| policy_loss | -0.149 |\n", + "| std | 0.0454 |\n", + "| value_loss | 0.00921 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 918 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 93200 |\n", + "| time_elapsed | 5908 |\n", + "| total_timesteps | 2982400 |\n", + "| train/ | |\n", + "| entropy_loss | -1.83 |\n", + "| explained_variance | 0.997 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 93199 |\n", + "| policy_loss | 0.0128 |\n", + "| std | 0.0453 |\n", + "| value_loss | 0.00116 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 916 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 93300 |\n", + "| time_elapsed | 5913 |\n", + "| total_timesteps | 2985600 |\n", + "| train/ | |\n", + "| entropy_loss | -2.22 |\n", + "| explained_variance | 0.996 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 93299 |\n", + "| policy_loss | 0.064 |\n", + "| std | 0.0453 |\n", + "| value_loss | 0.00135 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 919 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 93400 |\n", + "| time_elapsed | 5919 |\n", + "| total_timesteps | 2988800 |\n", + "| train/ | |\n", + "| entropy_loss | -2.18 |\n", + "| explained_variance | 0.99 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 93399 |\n", + "| policy_loss | -0.00869 |\n", + "| std | 0.0449 |\n", + "| value_loss | 0.00504 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 932 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 93500 |\n", + "| time_elapsed | 5926 |\n", + "| total_timesteps | 2992000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.96 |\n", + "| explained_variance | 0.988 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 93499 |\n", + "| policy_loss | 0.0199 |\n", + "| std | 0.045 |\n", + "| value_loss | 0.00329 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 941 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 93600 |\n", + "| time_elapsed | 5933 |\n", + "| total_timesteps | 2995200 |\n", + "| train/ | |\n", + "| entropy_loss | -2.18 |\n", + "| explained_variance | 0.982 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 93599 |\n", + "| policy_loss | 0.05 |\n", + "| std | 0.045 |\n", + "| value_loss | 0.00197 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 1e+03 |\n", + "| ep_rew_mean | 953 |\n", + "| time/ | |\n", + "| fps | 504 |\n", + "| iterations | 93700 |\n", + "| time_elapsed | 5941 |\n", + "| total_timesteps | 2998400 |\n", + "| train/ | |\n", + "| entropy_loss | -1.87 |\n", + "| explained_variance | 0.996 |\n", + "| learning_rate | 0.000969 |\n", + "| n_updates | 93699 |\n", + "| policy_loss | 0.00234 |\n", + "| std | 0.0449 |\n", + "| value_loss | 0.0013 |\n", + "------------------------------------\n" + ] + }, + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "" + ] + }, + "metadata": {}, + "execution_count": 12 + } + ] + }, + { + "cell_type": "code", + "source": [ + "notebook_login()\n", + "!git config --global credential.helper store" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 331, + "referenced_widgets": [ + "156c5533e16243a7bda1e84f80f5114e", + "a00a11e622d44f97a332fd474ce466cd", + "2b6fb2c35de748c08c963729d8e420ce", + "6b0b5d0652954f6788de81be2aed4a91", + "c2e98a3f69eb4567a59bfc3b2dc75d09", + "4f9c9bf144f24505ae9d7f37a2e08469", + "c0c745264866433d9a23bace3f6942ca", + "6b327d9a12d04092a0c35e22641749f6", + "605f13ce1adb4ec19fb28be89862662f", + "3458c418bf9e4790b3bb58eb411afa84", + "ec672f86dbe54f779c83a55e124d3529", + "487a8dfceb5d4c0c961920dd87f6c3dc", + "6006287334cb4569b285b532feeb1bac", + "3cb0781eaf4d40f192bd3c0e9b0e7754", + "e89bd84972124556842d0b8b88c53c82", + "9044266c2ffd42caa0fbca6a6c0cfe1c", + "59d495c7bac64601b8290f2b91a5f95a" + ] + }, + "id": "EbyyIWRYs-0Z", + "outputId": "9e1b9862-51f2-445a-8acb-42b9d7f43b29" + }, + "execution_count": 31, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Token is valid.\n", + "Your token has been saved in your configured git credential helpers (store).\n", + "Your token has been saved to /root/.cache/huggingface/token\n", + "Login successful\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "# Save the model and VecNormalize statistics when saving the agent\n", + "model.save(\"a2c-AntBulletEnv-v0\")\n", + "env.save(\"vec_normalize.pkl\")" + ], + "metadata": { + "id": "Bao6xqMOtPEK" + }, + "execution_count": 38, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "from stable_baselines3.common.vec_env import DummyVecEnv, VecNormalize\n", + "\n", + "# Load the saved statistics\n", + "eval_env = DummyVecEnv([lambda: gym.make(\"AntBulletEnv-v0\")])\n", + "eval_env = VecNormalize.load(\"vec_normalize.pkl\", eval_env)\n", + "\n", + "# do not update them at test time\n", + "eval_env.training = False\n", + "# reward normalization is not needed at test time\n", + "eval_env.norm_reward = False\n", + "\n", + "# Load the agent\n", + "model = A2C.load(\"a2c-AntBulletEnv-v0\")\n", + "\n", + "mean_reward, std_reward = evaluate_policy(model, eval_env)\n", + "\n", + "print(f\"Mean reward = {mean_reward:.2f} +/- {std_reward:.2f}\")" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "AFwGD_K3zBww", + "outputId": "331a209f-8db6-43cb-829f-376e73da9451" + }, + "execution_count": 39, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Mean reward = 547.70 +/- 111.52\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "package_to_hub(\n", + " model=model,\n", + " model_name=f\"a2c-{env_id}\",\n", + " model_architecture=\"A2C\",\n", + " env_id=env_id,\n", + " eval_env=eval_env,\n", + " repo_id=f\"DrishtiSharma/a2c-{env_id}\", # Change the username\n", + " commit_message=\"Initial commit\",\n", + ")" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 366, + "referenced_widgets": [ + "3f0e1549af384b5eaaf8d0e0947ffa63", + "2469c6a556f646ce948ebaf91538b6f9", + "edd595ea0bcb4405babbd89ce001b713", + "32befdf329704957a799f02d4b567809", + "20705240642b484e9d3600c1e1b59fd4", + "4df6f9ecc994445e869d4f166b993275", + "630be75737424612b4548699931d42a1", + "25ed9665e62541ccb2cb7c54abc9893a", + "f2bb94fa4b1f45a4b6a3b2733f286ee0", + "e9ee36a505784dffb619f0a371e1f30a", + "dd9c3c14cdc047608c52232da0922fbf", + "dbdf621979244bc884d5978a717964ec", + "2a0d9775e20848af8b1dd2d816c29c83", + "95aa8c1e9a16422d80c39b58a6f41be2", + "b517ca6b785e4f3da25f0ac3479baf27", + "13e80013881248a596b2f5e66ded6b78", + "91956ea4266f4f569b213216f4152b4a", + "3c32343528234482b6074b484eabf35b", + "ff3776982a9f447d9358034b6173810b", + "9beb866c18d642c09026f72b7162f705", + "dc4d21ed062441189ade718a1637ce15", + "d5dc4b70fddf44b69380a621dd07776f", + "0b1acf65b5d54bb2b7139d3ec608b1dc", + "8f49d8154ba141439baff19887525f58", + "adc728f4a9a34defbca502e64ecbd6bd", + "c8ac80f0d8a540f2a0f10f2c1de7120e", + "ab9d88cffbe44792b4f33f48a35ea207", + "0da068b4a75d4eba823d4b1524d383b9", + "db4ed7c243ff44779319129275047d19", + "a77ed51197ef4c8698000cd6486031ec", + "72f5f757970c42e9acfa251a43c78d29", + "b723acd11a59442a935c4bf48bd08cc2", + "ee40cee766c140f997d5d2e0df1791de", + "4c6ab63c95874d1e807d4b9d13ecbe71", + "46b2a515f62743f38e36bd34f3c4c25d", + "5027a441cf3f462baecc84aa26d9aaa9", + "65af073891b745749747b04a1109e3a7", + "5101355a7838441b86f3afe843d479b3", + "3a13164d7885436a8cc75f174ad1a800", + "31f4fc6dc22a47829f44408249d4d106", + "84df193e14c04a2286852ee3994de7ef", + "c7fcb03dc92e4e5b85d29e57fc36b6c7", + "b9bd6fdb316b46d1974c63deb3d592f3", + "ff3f469eff2148c192e618cfdf5af008", + "f228987c7fc64d30ba7c2f9d0ae971ab", + "052da86de60c4d42b9ff3443ae2167fd", + "8c5c76524e354e2da1155e0d2d16f14e", + "85a94779b184457d88483a0c653b6865", + "ba7239084fee470db29a8410cba7a859", + "273e4cb1ebc24a438700a8acb626453b", + "e8fb69888ba3487c9fa62449cbc665e8", + "0010ce3516404b229534792c804a2108", + "ec031f4349804865bf1a43c6a439f3ce", + "f1ea5d94c4fd4da7b9dbddf4baf51858", + "0342b70c06d54475aec9a096678976e8", + "70550b80f84f4c2c8a78507f4d4b7d7d", + "68b0a8b98bc64437b21321bc81ecabda", + "76792056dc8e41b8b429dbaedcc8b959", + "21dfca4be5ec4153a0092408c4cd8008", + "ae165b0638e44c7c8e4ed2883ad54780", + "457a90c53184449cb84aac8566a0c5ee", + "f65d8a0e537e42aeb05ad14d01736838", + "893f301fae2d407b88fa5222b33960e8", + "e890edf0b0db4e29b6bae6e255e7ea60", + "a3f2601e95cc46fba98c2b831a90c590", + "cb1b15ddb2aa4cc7b4816fbff9c264ec" + ] + }, + "id": "5Rf7sQ-UzGkY", + "outputId": "da474fc2-986f-4ab5-bd8c-d8eaf91b558a" + }, + "execution_count": 40, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\u001b[38;5;4mℹ This function will save, evaluate, generate a video of your agent,\n", + "create a model card and push everything to the hub. It might take up to 1min.\n", + "This is a work in progress: if you encounter a bug, please open an issue.\u001b[0m\n", + "Saving video to /tmp/tmpkksh1ofu/-step-0-to-step-1000.mp4\n", + "\u001b[38;5;4mℹ Pushing repo DrishtiSharma/a2c-AntBulletEnv-v0 to the Hugging Face\n", + "Hub\u001b[0m\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "policy.optimizer.pth: 0%| | 0.00/56.2k [00:00