Initial commit

DDPG-PandaReach-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdb9b4fca65f9adf4d40f6b29ddc38a3a8c368f91c7ae0b9d331b6b4ef1f2125
+size 4091733

DDPG-PandaReach-v3/_stable_baselines3_version

@@ -0,0 +1 @@
+2.2.1

DDPG-PandaReach-v3/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:504e834fa1edeb78ad6ce4bd04284947690c11601c8297e87c61cb40c2c0df7a
+size 1016544

DDPG-PandaReach-v3/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17d328fd90b3d1bc5276fe3bcf751a94792dde3d76a17dd0327de1ee6286474f
+size 1021280

DDPG-PandaReach-v3/data

@@ -0,0 +1,120 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVNwAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnRkMy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu",
+        "__module__": "stable_baselines3.td3.policies",
+        "__doc__": "\n    Policy class (with both actor and critic) for TD3 to be used with Dict observation spaces.\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 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    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ",
+        "__init__": "<function MultiInputPolicy.__init__ at 0x784654cb9b40>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x784654cbcc40>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "n_critics": 1
+    },
+    "num_timesteps": 30011,
+    "_total_timesteps": 30000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1700567699907138358,
+    "learning_rate": 0.001,
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'collections.OrderedDict'>",
+        ":serialized:": "gAWVKwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAA6nIdPRlsGqxDI0o+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAADdoQvoVdTb2Mvw4+lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWGAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAACUaA5LAUsGhpRoEnSUUpR1Lg==",
+        "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]]",
+        "desired_goal": "[[-0.1414568  -0.05013802  0.13940257]]",
+        "observation": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]]"
+    },
+    "_episode_num": 7512,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.0003666666666666263,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiJiIiIiYiIiIiJiIiIiImJiIiJiIiIiIiIiYiJiYiIiYiIiYmJiYmJiImIiYmJiImIiImIiYiIiYmJiYmJiImIiYmIiYiJiYmIiYmJiYmJiYiJiYmJiImJiYmJiYmJiYmJiYllLg=="
+    },
+    "_n_updates": 29911,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.dict.Dict'>",
+        ":serialized:": "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",
+        "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])",
+        "_shape": null,
+        "dtype": null,
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "gAWVRgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAwAAAAAAAAABAQGUaAiMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLA4WUjAFDlHSUUpSMDWJvdW5kZWRfYWJvdmWUaBEolgMAAAAAAAAAAQEBlGgVSwOFlGgZdJRSlIwGX3NoYXBllEsDhZSMA2xvd5RoESiWDAAAAAAAAAAAAIC/AACAvwAAgL+UaAtLA4WUaBl0lFKUjARoaWdolGgRKJYMAAAAAAAAAAAAgD8AAIA/AACAP5RoC0sDhZRoGXSUUpSMCGxvd19yZXBylIwELTEuMJSMCWhpZ2hfcmVwcpSMAzEuMJSMCl9ucF9yYW5kb22UjBRudW1weS5yYW5kb20uX3BpY2tsZZSMEF9fZ2VuZXJhdG9yX2N0b3KUk5SMBVBDRzY0lIWUUpR9lCiMDWJpdF9nZW5lcmF0b3KUjAVQQ0c2NJSMBXN0YXRllH2UKGg7ihHkLwgklEH+q4C6pPQwKuOvAIwDaW5jlIoQgdLHs2CbFHslfu2ZleUwXXWMCmhhc191aW50MzKUSwCMCHVpbnRlZ2VylEsAdWJ1Yi4=",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True]",
+        "bounded_above": "[ True  True  True]",
+        "_shape": [
+            3
+        ],
+        "low": "[-1. -1. -1.]",
+        "high": "[1. 1. 1.]",
+        "low_repr": "-1.0",
+        "high_repr": "1.0",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
+    "buffer_size": 1000000,
+    "batch_size": 100,
+    "learning_starts": 100,
+    "tau": 0.005,
+    "gamma": 0.99,
+    "gradient_steps": -1,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVPwAAAAAAAACMJ3N0YWJsZV9iYXNlbGluZXMzLmhlci5oZXJfcmVwbGF5X2J1ZmZlcpSMD0hlclJlcGxheUJ1ZmZlcpSTlC4=",
+        "__module__": "stable_baselines3.her.her_replay_buffer",
+        "__annotations__": "{'env': typing.Optional[stable_baselines3.common.vec_env.base_vec_env.VecEnv]}",
+        "__doc__": "\n    Hindsight Experience Replay (HER) buffer.\n    Paper: https://arxiv.org/abs/1707.01495\n\n    Replay buffer for sampling HER (Hindsight Experience Replay) transitions.\n\n    .. note::\n\n      Compared to other implementations, the ``future`` goal sampling strategy is inclusive:\n      the current transition can be used when re-sampling.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param env: The training environment\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        Disabled for now (see https://github.com/DLR-RM/stable-baselines3/pull/243#discussion_r531535702)\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    :param n_sampled_goal: Number of virtual transitions to create per real transition,\n        by sampling new goals.\n    :param goal_selection_strategy: Strategy for sampling goals for replay.\n        One of ['episode', 'final', 'future']\n    :param copy_info_dict: Whether to copy the info dictionary and pass it to\n        ``compute_reward()`` method.\n        Please note that the copy may cause a slowdown.\n        False by default.\n    ",
+        "__init__": "<function HerReplayBuffer.__init__ at 0x784654cba7a0>",
+        "__getstate__": "<function HerReplayBuffer.__getstate__ at 0x784654cba830>",
+        "__setstate__": "<function HerReplayBuffer.__setstate__ at 0x784654cba8c0>",
+        "set_env": "<function HerReplayBuffer.set_env at 0x784654cba950>",
+        "add": "<function HerReplayBuffer.add at 0x784654cba9e0>",
+        "_compute_episode_length": "<function HerReplayBuffer._compute_episode_length at 0x784654cbaa70>",
+        "sample": "<function HerReplayBuffer.sample at 0x784654cbab00>",
+        "_get_real_samples": "<function HerReplayBuffer._get_real_samples at 0x784654cbab90>",
+        "_get_virtual_samples": "<function HerReplayBuffer._get_virtual_samples at 0x784654cbac20>",
+        "_sample_goals": "<function HerReplayBuffer._sample_goals at 0x784654cbacb0>",
+        "truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x784654cbad40>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x784654cbfe40>"
+    },
+    "replay_buffer_kwargs": {
+        "n_sampled_goal": 4,
+        "goal_selection_strategy": "future"
+    },
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVZAAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMB2VwaXNvZGWUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "policy_delay": 1,
+    "target_noise_clip": 0.0,
+    "target_policy_noise": 0.1,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "actor_batch_norm_stats": [],
+    "critic_batch_norm_stats": [],
+    "actor_batch_norm_stats_target": [],
+    "critic_batch_norm_stats_target": []
+}

DDPG-PandaReach-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d58aa081a2e97cd5dfa0715dbd43bc4e7a00a5fb1130a98943b0fb5c63f3bb9
+size 2036558

DDPG-PandaReach-v3/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

DDPG-PandaReach-v3/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.2.1
+- PyTorch: 2.1.0+cu118
+- GPU Enabled: True
+- Numpy: 1.23.5
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.25.2

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- PandaReach-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: DDPG
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: PandaReach-v3
+      type: PandaReach-v3
+    metrics:
+    - type: mean_reward
+      value: -45.00 +/- 15.00
+      name: mean_reward
+      verified: false
+---
+
+# **DDPG** Agent playing **PandaReach-v3**
+This is a trained model of a **DDPG** agent playing **PandaReach-v3**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+
+## Usage (with Stable-baselines3)
+TODO: Add your code
+
+
+```python
+from stable_baselines3 import ...
+from huggingface_sb3 import load_from_hub
+
+...
+```

config.json

@@ -0,0 +1 @@
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNwAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnRkMy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu", "__module__": "stable_baselines3.td3.policies", "__doc__": "\n    Policy class (with both actor and critic) for TD3 to be used with Dict observation spaces.\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 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    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ", "__init__": "<function MultiInputPolicy.__init__ at 0x784654cb9b40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x784654cbcc40>"}, "verbose": 1, "policy_kwargs": {"n_critics": 1}, "num_timesteps": 30011, "_total_timesteps": 30000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1700567699907138358, "learning_rate": 0.001, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "gAWVKwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAA6nIdPRlsGqxDI0o+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAADdoQvoVdTb2Mvw4+lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWGAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAACUaA5LAUsGhpRoEnSUUpR1Lg==", "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]]", "desired_goal": "[[-0.1414568  -0.05013802  0.13940257]]", "observation": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]]"}, "_episode_num": 7512, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0003666666666666263, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiJiIiIiYiIiIiJiIiIiImJiIiJiIiIiIiIiYiJiYiIiYiIiYmJiYmJiImIiYmJiImIiImIiYiIiYmJiYmJiImIiYmIiYiJiYmIiYmJiYmJiYiJiYmJiImJiYmJiYmJiYmJiYllLg=="}, "_n_updates": 29911, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True]", "bounded_above": "[ True  True  True]", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": "Generator(PCG64)"}, "n_envs": 1, "buffer_size": 1000000, "batch_size": 100, "learning_starts": 100, "tau": 0.005, "gamma": 0.99, "gradient_steps": -1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVPwAAAAAAAACMJ3N0YWJsZV9iYXNlbGluZXMzLmhlci5oZXJfcmVwbGF5X2J1ZmZlcpSMD0hlclJlcGxheUJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.her.her_replay_buffer", "__annotations__": "{'env': typing.Optional[stable_baselines3.common.vec_env.base_vec_env.VecEnv]}", "__doc__": "\n    Hindsight Experience Replay (HER) buffer.\n    Paper: https://arxiv.org/abs/1707.01495\n\n    Replay buffer for sampling HER (Hindsight Experience Replay) transitions.\n\n    .. note::\n\n      Compared to other implementations, the ``future`` goal sampling strategy is inclusive:\n      the current transition can be used when re-sampling.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param env: The training environment\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        Disabled for now (see https://github.com/DLR-RM/stable-baselines3/pull/243#discussion_r531535702)\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    :param n_sampled_goal: Number of virtual transitions to create per real transition,\n        by sampling new goals.\n    :param goal_selection_strategy: Strategy for sampling goals for replay.\n        One of ['episode', 'final', 'future']\n    :param copy_info_dict: Whether to copy the info dictionary and pass it to\n        ``compute_reward()`` method.\n        Please note that the copy may cause a slowdown.\n        False by default.\n    ", "__init__": "<function HerReplayBuffer.__init__ at 0x784654cba7a0>", "__getstate__": "<function HerReplayBuffer.__getstate__ at 0x784654cba830>", "__setstate__": "<function HerReplayBuffer.__setstate__ at 0x784654cba8c0>", "set_env": "<function HerReplayBuffer.set_env at 0x784654cba950>", "add": "<function HerReplayBuffer.add at 0x784654cba9e0>", "_compute_episode_length": "<function HerReplayBuffer._compute_episode_length at 0x784654cbaa70>", "sample": "<function HerReplayBuffer.sample at 0x784654cbab00>", "_get_real_samples": "<function HerReplayBuffer._get_real_samples at 0x784654cbab90>", "_get_virtual_samples": "<function HerReplayBuffer._get_virtual_samples at 0x784654cbac20>", "_sample_goals": "<function HerReplayBuffer._sample_goals at 0x784654cbacb0>", "truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x784654cbad40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x784654cbfe40>"}, "replay_buffer_kwargs": {"n_sampled_goal": 4, "goal_selection_strategy": "future"}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVZAAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMB2VwaXNvZGWUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "policy_delay": 1, "target_noise_clip": 0.0, "target_policy_noise": 0.1, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "actor_batch_norm_stats": [], "critic_batch_norm_stats": [], "actor_batch_norm_stats_target": [], "critic_batch_norm_stats_target": [], "system_info": {"OS": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.2.1", "PyTorch": "2.1.0+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.25.2"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": -45.0, "std_reward": 15.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-21T12:03:33.061845"}

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17069d2d17900258df1b104181d83fc27720640c99a026007ee6e4a3b6b19338
+size 2803