Initial commit

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- PandaReachDense-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: PandaReachDense-v3
+      type: PandaReachDense-v3
+    metrics:
+    - type: mean_reward
+      value: -0.19 +/- 0.08
+      name: mean_reward
+      verified: false
+---
+
+# **SAC** Agent playing **PandaReachDense-v3**
+This is a trained model of a **SAC** agent playing **PandaReachDense-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
+
+...
+```

SAC-PandaReachDense-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:535adec259b91b9c19f77dc9aab577817dc6087cf4f202752ff77b4e9c37f6c4
+size 3143096

SAC-PandaReachDense-v3/_stable_baselines3_version

@@ -0,0 +1 @@
+2.3.2

SAC-PandaReachDense-v3/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:945a0c2ff3c6e0bbff3257a0bd3370ebb7b29bd5819efe066ced03cf3dcf9bf0
+size 572238

SAC-PandaReachDense-v3/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1f6799bb951c884bb915ee72caf666de97eaf54b37a5d83ab3c5ddec0d53c82
+size 1132458

SAC-PandaReachDense-v3/data

@@ -0,0 +1,114 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVNwAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu",
+        "__module__": "stable_baselines3.sac.policies",
+        "__doc__": "\n    Policy class (with both actor and critic) for SAC.\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 use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n    :param features_extractor_class: Features extractor to use.\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 0x78dc28067520>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x78dc28077340>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "use_sde": false
+    },
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1717179402744285910,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'collections.OrderedDict'>",
+        ":serialized:": "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",
+        "achieved_goal": "[[ 8.0869421e-02  6.9819063e-02  2.3513584e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 2.4917977e-02  2.0068793e-03  1.6584681e-01]\n [ 6.7383267e-02  6.3651837e-02  1.2071376e-01]]",
+        "desired_goal": "[[ 0.13657327  0.09641358  0.2570357 ]\n [-0.08409639  0.12845945  0.17110576]\n [ 0.02242014  0.02141123  0.08677045]\n [ 0.08652944  0.11747987  0.03867379]]",
+        "observation": "[[ 8.08694214e-02  6.98190629e-02  2.35135838e-01  2.45760038e-01\n   5.93530715e-01  4.39599782e-01]\n [ 3.84396687e-02 -2.19447225e-12  1.97400138e-01  0.00000000e+00\n  -0.00000000e+00  0.00000000e+00]\n [ 2.49179769e-02  2.00687931e-03  1.65846810e-01 -6.45017564e-01\n   1.39819905e-02 -1.11986482e+00]\n [ 6.73832670e-02  6.36518374e-02  1.20713763e-01 -2.47442890e-02\n   3.88643235e-01 -1.37708223e+00]]"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'collections.OrderedDict'>",
+        ":serialized:": "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",
+        "achieved_goal": "[[ 5.4628022e-02  2.4599239e-02  2.0969182e-01]\n [ 5.1618129e-02  1.4066349e-02  2.1282546e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 4.9814299e-02  2.4144897e-02  1.7482617e-01]]",
+        "desired_goal": "[[0.13657327 0.09641358 0.2570357 ]\n [0.10931625 0.02049003 0.25801346]\n [0.02242014 0.02141123 0.08677045]\n [0.08652944 0.11747987 0.03867379]]",
+        "observation": "[[ 5.4628022e-02  2.4599239e-02  2.0969182e-01  4.8645595e-01\n   1.0775303e+00  5.3511131e-01]\n [ 5.1618129e-02  1.4066349e-02  2.1282546e-01  5.1350808e-01\n   2.1939233e-01  6.7332393e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 4.9814299e-02  2.4144897e-02  1.7482617e-01 -2.2942826e-01\n   1.0088108e+00 -1.3363283e+00]]"
+    },
+    "_episode_num": 331113,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.0,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIhlLg=="
+    },
+    "_n_updates": 249975,
+    "buffer_size": 1000000,
+    "batch_size": 256,
+    "learning_starts": 100,
+    "tau": 0.005,
+    "gamma": 0.99,
+    "gradient_steps": 1,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVOQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwQRGljdFJlcGxheUJ1ZmZlcpSTlC4=",
+        "__module__": "stable_baselines3.common.buffers",
+        "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray], 'next_observations': typing.Dict[str, numpy.ndarray]}",
+        "__doc__": "\n    Dict Replay buffer used in off-policy algorithms like SAC/TD3.\n    Extends the ReplayBuffer to use dictionary observations\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 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    ",
+        "__init__": "<function DictReplayBuffer.__init__ at 0x78dc27f83400>",
+        "add": "<function DictReplayBuffer.add at 0x78dc27f83490>",
+        "sample": "<function DictReplayBuffer.sample at 0x78dc27f83520>",
+        "_get_samples": "<function DictReplayBuffer._get_samples at 0x78dc27f835b0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x78dc282679c0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -3.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "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": 4,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": []
+}

SAC-PandaReachDense-v3/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48f862cf0c9d9fe111ba93e3efc4b5bfa1a49d393cff5f0a72aa965a88ff098d
+size 1940

SAC-PandaReachDense-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5703b07f13823a50299cabf0a5dcafd6b52143dd445ac6e66f9b07261f8ee5b5
+size 1417078

SAC-PandaReachDense-v3/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c79e8507480cde6329b2b51ef18bf5a6a67bfd8c9a43041a360316d49e304f37
+size 1180

SAC-PandaReachDense-v3/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024
+- Python: 3.10.12
+- Stable-Baselines3: 2.3.2
+- PyTorch: 2.3.0+cu121
+- GPU Enabled: True
+- Numpy: 1.25.2
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.25.2

config.json

@@ -0,0 +1 @@
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNwAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu", "__module__": "stable_baselines3.sac.policies", "__doc__": "\n    Policy class (with both actor and critic) for SAC.\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 use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n    :param features_extractor_class: Features extractor to use.\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 0x78dc28067520>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78dc28077340>"}, "verbose": 1, "policy_kwargs": {"use_sde": false}, "num_timesteps": 1000000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1717179402744285910, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 8.0869421e-02  6.9819063e-02  2.3513584e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 2.4917977e-02  2.0068793e-03  1.6584681e-01]\n [ 6.7383267e-02  6.3651837e-02  1.2071376e-01]]", "desired_goal": "[[ 0.13657327  0.09641358  0.2570357 ]\n [-0.08409639  0.12845945  0.17110576]\n [ 0.02242014  0.02141123  0.08677045]\n [ 0.08652944  0.11747987  0.03867379]]", "observation": "[[ 8.08694214e-02  6.98190629e-02  2.35135838e-01  2.45760038e-01\n   5.93530715e-01  4.39599782e-01]\n [ 3.84396687e-02 -2.19447225e-12  1.97400138e-01  0.00000000e+00\n  -0.00000000e+00  0.00000000e+00]\n [ 2.49179769e-02  2.00687931e-03  1.65846810e-01 -6.45017564e-01\n   1.39819905e-02 -1.11986482e+00]\n [ 6.73832670e-02  6.36518374e-02  1.20713763e-01 -2.47442890e-02\n   3.88643235e-01 -1.37708223e+00]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 5.4628022e-02  2.4599239e-02  2.0969182e-01]\n [ 5.1618129e-02  1.4066349e-02  2.1282546e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 4.9814299e-02  2.4144897e-02  1.7482617e-01]]", "desired_goal": "[[0.13657327 0.09641358 0.2570357 ]\n [0.10931625 0.02049003 0.25801346]\n [0.02242014 0.02141123 0.08677045]\n [0.08652944 0.11747987 0.03867379]]", "observation": "[[ 5.4628022e-02  2.4599239e-02  2.0969182e-01  4.8645595e-01\n   1.0775303e+00  5.3511131e-01]\n [ 5.1618129e-02  1.4066349e-02  2.1282546e-01  5.1350808e-01\n   2.1939233e-01  6.7332393e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 4.9814299e-02  2.4144897e-02  1.7482617e-01 -2.2942826e-01\n   1.0088108e+00 -1.3363283e+00]]"}, "_episode_num": 331113, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIhlLg=="}, "_n_updates": 249975, "buffer_size": 1000000, "batch_size": 256, "learning_starts": 100, "tau": 0.005, "gamma": 0.99, "gradient_steps": 1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwQRGljdFJlcGxheUJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray], 'next_observations': typing.Dict[str, numpy.ndarray]}", "__doc__": "\n    Dict Replay buffer used in off-policy algorithms like SAC/TD3.\n    Extends the ReplayBuffer to use dictionary observations\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 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    ", "__init__": "<function DictReplayBuffer.__init__ at 0x78dc27f83400>", "add": "<function DictReplayBuffer.add at 0x78dc27f83490>", "sample": "<function DictReplayBuffer.sample at 0x78dc27f83520>", "_get_samples": "<function DictReplayBuffer._get_samples at 0x78dc27f835b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78dc282679c0>"}, "replay_buffer_kwargs": {}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "target_entropy": -3.0, "ent_coef": "auto", "target_update_interval": 1, "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": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "batch_norm_stats": [], "batch_norm_stats_target": [], "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.3.2", "PyTorch": "2.3.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.25.2"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": -0.19165178798139096, "std_reward": 0.08107273754068507, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-31T19:59:17.007511"}

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94bf28f7657cc652023b80dd63238c7d555be931c7fa05e5844ac6dc967352d1
+size 2633