osanseviero HF staff commited on
Commit
93618b0
1 Parent(s): 7d94058

Test commit

Browse files
-step-0-to-step-1000.meta.json CHANGED
@@ -1 +1 @@
1
- {"step_id": 0, "content_type": "video/mp4", "encoder_version": {"backend": "ffmpeg", "version": "b'ffmpeg version 4.2.7-0ubuntu0.1 Copyright (c) 2000-2022 the FFmpeg developers\\nbuilt with gcc 9 (Ubuntu 9.4.0-1ubuntu1~20.04.1)\\nconfiguration: --prefix=/usr --extra-version=0ubuntu0.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-avresample --disable-filter=resample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librsvg --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-nvenc --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared\\nlibavutil 56. 31.100 / 56. 31.100\\nlibavcodec 58. 54.100 / 58. 54.100\\nlibavformat 58. 29.100 / 58. 29.100\\nlibavdevice 58. 8.100 / 58. 8.100\\nlibavfilter 7. 57.100 / 7. 57.100\\nlibavresample 4. 0. 0 / 4. 0. 0\\nlibswscale 5. 5.100 / 5. 5.100\\nlibswresample 3. 5.100 / 3. 5.100\\nlibpostproc 55. 5.100 / 55. 5.100\\n'", "cmdline": ["ffmpeg", "-nostats", "-loglevel", "error", "-y", "-f", "rawvideo", "-s:v", "600x400", "-pix_fmt", "rgb24", "-r", "50", "-i", "-", "-an", "-r", "50", "-vcodec", "mpeg4", "-pix_fmt", "bgr24", "-r", "50", "/tmp/tmpzxd96yqf/-step-0-to-step-1000.mp4"]}}
 
1
+ {"step_id": 0, "content_type": "video/mp4", "encoder_version": {"backend": "ffmpeg", "version": "b'ffmpeg version 4.2.7-0ubuntu0.1 Copyright (c) 2000-2022 the FFmpeg developers\\nbuilt with gcc 9 (Ubuntu 9.4.0-1ubuntu1~20.04.1)\\nconfiguration: --prefix=/usr --extra-version=0ubuntu0.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-avresample --disable-filter=resample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librsvg --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-nvenc --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared\\nlibavutil 56. 31.100 / 56. 31.100\\nlibavcodec 58. 54.100 / 58. 54.100\\nlibavformat 58. 29.100 / 58. 29.100\\nlibavdevice 58. 8.100 / 58. 8.100\\nlibavfilter 7. 57.100 / 7. 57.100\\nlibavresample 4. 0. 0 / 4. 0. 0\\nlibswscale 5. 5.100 / 5. 5.100\\nlibswresample 3. 5.100 / 3. 5.100\\nlibpostproc 55. 5.100 / 55. 5.100\\n'", "cmdline": ["ffmpeg", "-nostats", "-loglevel", "error", "-y", "-f", "rawvideo", "-s:v", "600x400", "-pix_fmt", "rgb24", "-r", "50", "-i", "-", "-an", "-r", "50", "-vcodec", "mpeg4", "-pix_fmt", "bgr24", "-r", "50", "/tmp/tmpanjmgpk2/-step-0-to-step-1000.mp4"]}}
-step-0-to-step-1000.mp4 CHANGED
Binary files a/-step-0-to-step-1000.mp4 and b/-step-0-to-step-1000.mp4 differ
 
README.md CHANGED
@@ -10,7 +10,7 @@ model-index:
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
- value: -495.80 +/- 0.00
14
  name: mean_reward
15
  task:
16
  type: reinforcement-learning
 
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
+ value: -443.18 +/- 0.00
14
  name: mean_reward
15
  task:
16
  type: reinforcement-learning
config.json CHANGED
@@ -1 +1 @@
1
- {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7fb92d6e4430>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb92d6e44c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb92d6e4550>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb92d6e45e0>", "_build": "<function ActorCriticPolicy._build at 0x7fb92d6e4670>", "forward": "<function ActorCriticPolicy.forward at 0x7fb92d6e4700>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb92d6e4790>", "_predict": "<function ActorCriticPolicy._predict at 0x7fb92d6e4820>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb92d6e48b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb92d6e4940>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb92d6e49d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fb92d74cae0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVgQAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc2hhcGWUKYwFZHR5cGWUjAVudW1weZRoB5OUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijApfbnBfcmFuZG9tlE51Yi4=", "n": 4, "shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 2048, "_total_timesteps": 10, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1657184897.6910481, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAANISrr4+I7w9SmAvv8MMr780Nzc/DAiyvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -203.8, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 10, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "target_kl": null, "system_info": {"OS": "Linux-5.13.0-52-generic-x86_64-with-glibc2.17 #59~20.04.1-Ubuntu SMP Thu Jun 16 21:21:28 UTC 2022", "Python": "3.8.13", "Stable-Baselines3": "1.4.0", "PyTorch": "1.12.0+cu102", "GPU Enabled": "True", "Numpy": "1.23.0", "Gym": "0.19.0"}}
 
1
+ {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7fd9a904d430>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd9a904d4c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd9a904d550>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd9a904d5e0>", "_build": "<function ActorCriticPolicy._build at 0x7fd9a904d670>", "forward": "<function ActorCriticPolicy.forward at 0x7fd9a904d700>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd9a904d790>", "_predict": "<function ActorCriticPolicy._predict at 0x7fd9a904d820>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd9a904d8b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd9a904d940>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd9a904d9d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fd9a90b5ae0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVgQAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc2hhcGWUKYwFZHR5cGWUjAVudW1weZRoB5OUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijApfbnBfcmFuZG9tlE51Yi4=", "n": 4, "shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 2048, "_total_timesteps": 10, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1657186133.590796, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGaSd702xUI/eyP+vR2/V79j/Js9WaygPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -203.8, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 10, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "target_kl": null, "system_info": {"OS": "Linux-5.13.0-52-generic-x86_64-with-glibc2.17 #59~20.04.1-Ubuntu SMP Thu Jun 16 21:21:28 UTC 2022", "Python": "3.8.13", "Stable-Baselines3": "1.4.0", "PyTorch": "1.12.0+cu102", "GPU Enabled": "True", "Numpy": "1.23.0", "Gym": "0.19.0"}}
ppo-LunarLander-v2.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c90796f7758f308c7bc82106371cca7a1aa5e08347a6fc1e3d5463295ec39737
3
- size 141436
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee4f06cbc56803cde8eca0e4b837dd7793e3ba27160def05f5d838eefd7c484d
3
+ size 141435
ppo-LunarLander-v2/data CHANGED
@@ -4,19 +4,19 @@
4
  ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
5
  "__module__": "stable_baselines3.common.policies",
6
  "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
7
- "__init__": "<function ActorCriticPolicy.__init__ at 0x7fb92d6e4430>",
8
- "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb92d6e44c0>",
9
- "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb92d6e4550>",
10
- "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb92d6e45e0>",
11
- "_build": "<function ActorCriticPolicy._build at 0x7fb92d6e4670>",
12
- "forward": "<function ActorCriticPolicy.forward at 0x7fb92d6e4700>",
13
- "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb92d6e4790>",
14
- "_predict": "<function ActorCriticPolicy._predict at 0x7fb92d6e4820>",
15
- "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb92d6e48b0>",
16
- "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb92d6e4940>",
17
- "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb92d6e49d0>",
18
  "__abstractmethods__": "frozenset()",
19
- "_abc_impl": "<_abc_data object at 0x7fb92d74cae0>"
20
  },
21
  "verbose": 1,
22
  "policy_kwargs": {},
@@ -47,7 +47,7 @@
47
  "_num_timesteps_at_start": 0,
48
  "seed": null,
49
  "action_noise": null,
50
- "start_time": 1657184897.6910481,
51
  "learning_rate": 0.0003,
52
  "tensorboard_log": null,
53
  "lr_schedule": {
@@ -56,7 +56,7 @@
56
  },
57
  "_last_obs": {
58
  ":type:": "<class 'numpy.ndarray'>",
59
- ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAANISrr4+I7w9SmAvv8MMr780Nzc/DAiyvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
60
  },
61
  "_last_episode_starts": {
62
  ":type:": "<class 'numpy.ndarray'>",
@@ -69,7 +69,7 @@
69
  "_current_progress_remaining": -203.8,
70
  "ep_info_buffer": {
71
  ":type:": "<class 'collections.deque'>",
72
- ":serialized:": "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"
73
  },
74
  "ep_success_buffer": {
75
  ":type:": "<class 'collections.deque'>",
 
4
  ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
5
  "__module__": "stable_baselines3.common.policies",
6
  "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
7
+ "__init__": "<function ActorCriticPolicy.__init__ at 0x7fd9a904d430>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd9a904d4c0>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd9a904d550>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd9a904d5e0>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7fd9a904d670>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7fd9a904d700>",
13
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd9a904d790>",
14
+ "_predict": "<function ActorCriticPolicy._predict at 0x7fd9a904d820>",
15
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd9a904d8b0>",
16
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd9a904d940>",
17
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd9a904d9d0>",
18
  "__abstractmethods__": "frozenset()",
19
+ "_abc_impl": "<_abc_data object at 0x7fd9a90b5ae0>"
20
  },
21
  "verbose": 1,
22
  "policy_kwargs": {},
 
47
  "_num_timesteps_at_start": 0,
48
  "seed": null,
49
  "action_noise": null,
50
+ "start_time": 1657186133.590796,
51
  "learning_rate": 0.0003,
52
  "tensorboard_log": null,
53
  "lr_schedule": {
 
56
  },
57
  "_last_obs": {
58
  ":type:": "<class 'numpy.ndarray'>",
59
+ ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGaSd702xUI/eyP+vR2/V79j/Js9WaygPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
60
  },
61
  "_last_episode_starts": {
62
  ":type:": "<class 'numpy.ndarray'>",
 
69
  "_current_progress_remaining": -203.8,
70
  "ep_info_buffer": {
71
  ":type:": "<class 'collections.deque'>",
72
+ ":serialized:": "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"
73
  },
74
  "ep_success_buffer": {
75
  ":type:": "<class 'collections.deque'>",
ppo-LunarLander-v2/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eba054a4f729f179227f04cc66c1ef76ebbb22ce24c364bfbe64bec9bf11b547
3
  size 87545
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78810cee1eca1bacd4160ff64a47efb3e0c79b3786aec7b57929b0185e801f68
3
  size 87545
ppo-LunarLander-v2/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae26fd956a89f7ca1468bfb7f41964924dc564b037fb524f6e263a142874b4b2
3
  size 43073
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54de992300ade27fd6a54a976ec6c2c73d1a7c376276495c1965332c5501970b
3
  size 43073
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": -495.797878, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 1, "eval_datetime": "2022-07-07T11:08:20.908807"}
 
1
+ {"mean_reward": -443.177299, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 1, "eval_datetime": "2022-07-07T11:28:56.687710"}