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: A2C
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: PandaReachDense-v3
+      type: PandaReachDense-v3
+    metrics:
+    - type: mean_reward
+      value: -0.12 +/- 0.11
+      name: mean_reward
+      verified: false
+---
+
+# **A2C** Agent playing **PandaReachDense-v3**
+This is a trained model of a **A2C** 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
+
+...
+```

a2c-PandaReachDense-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fe6e29efbef23514f70d8584a922347623f286bc8c66dff19d23c53789e8a45
+size 3141749

a2c-PandaReachDense-v3/_stable_baselines3_version

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

a2c-PandaReachDense-v3/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc98cb201569b0e2316006f183ce87790edd54b17958628d7919d8da0bb5c0b6
+size 571982

a2c-PandaReachDense-v3/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d7441af48da3010174efe56278a7c4d502b1c332846d637019d59694f4820ab
+size 1131946

a2c-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 0x7e1d838b79a0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7e1d836c3f40>"
+    },
+    "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": 1717678889523985754,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'collections.OrderedDict'>",
+        ":serialized:": "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",
+        "achieved_goal": "[[ 0.48593724  0.41881633  0.8182322 ]\n [ 0.32318288 -0.06420207  0.53251487]\n [ 0.32318288 -0.06420207  0.53251487]\n [ 0.32318288 -0.06420207  0.53251487]]",
+        "desired_goal": "[[ 0.6753942   0.8989489   1.0297809 ]\n [ 0.7468885   0.1281578  -0.5890698 ]\n [ 0.39018017 -0.34852502  0.883982  ]\n [-0.3158677   0.18268321 -1.1175094 ]]",
+        "observation": "[[ 0.48593724  0.41881633  0.8182322   1.2937069   1.922245    1.4677873 ]\n [ 0.32318288 -0.06420207  0.53251487  0.52614737 -0.01287868  0.3685873 ]\n [ 0.32318288 -0.06420207  0.53251487  0.52614737 -0.01287868  0.3685873 ]\n [ 0.32318288 -0.06420207  0.53251487  0.52614737 -0.01287868  0.3685873 ]]"
+    },
+    "_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": "[[ 4.6467911e-02  2.4478629e-02  2.1392143e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]]",
+        "desired_goal": "[[ 0.05577144  0.08033716  0.2362584 ]\n [ 0.06229192  0.01104843  0.08893096]\n [ 0.02975916 -0.03180202  0.22298962]\n [-0.03463429  0.01594988  0.04083902]]",
+        "observation": "[[ 4.6467911e-02  2.4478629e-02  2.1392143e-01  2.7916941e-01\n   1.1131716e+00  6.8653351e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]]"
+    },
+    "_episode_num": 302180,
+    "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 0x7e1d837df880>",
+        "add": "<function DictReplayBuffer.add at 0x7e1d837df910>",
+        "sample": "<function DictReplayBuffer.sample at 0x7e1d837df9a0>",
+        "_get_samples": "<function DictReplayBuffer._get_samples at 0x7e1d837dfa30>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7e1d837ec440>"
+    },
+    "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:": "gAWVYAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAwAAAAAAAAABAQGUaAiMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLA4WUjAFDlHSUUpSMDWJvdW5kZWRfYWJvdmWUaBEolgMAAAAAAAAAAQEBlGgVSwOFlGgZdJRSlIwGX3NoYXBllEsDhZSMA2xvd5RoESiWDAAAAAAAAAAAAIC/AACAvwAAgL+UaAtLA4WUaBl0lFKUjARoaWdolGgRKJYMAAAAAAAAAAAAgD8AAIA/AACAP5RoC0sDhZRoGXSUUpSMCGxvd19yZXBylIwELTEuMJSMCWhpZ2hfcmVwcpSMAzEuMJSMCl9ucF9yYW5kb22UjBRudW1weS5yYW5kb20uX3BpY2tsZZSMEF9fZ2VuZXJhdG9yX2N0b3KUk5SMBVBDRzY0lGgyjBRfX2JpdF9nZW5lcmF0b3JfY3RvcpSTlIaUUpR9lCiMDWJpdF9nZW5lcmF0b3KUjAVQQ0c2NJSMBXN0YXRllH2UKGg9ihDl+mJ4X7Ud8MLBboLmhfoZjANpbmOUihDntzp6uS6uIsdbqzCZ8jcldYwKaGFzX3VpbnQzMpRLAIwIdWludGVnZXKUSwB1YnViLg==",
+        "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": []
+}

a2c-PandaReachDense-v3/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40f372878eefb930be0e346b367b197ac22eb24b823607adff0cffdbf6524656
+size 1940

a2c-PandaReachDense-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb13c26918c49007dc7d49b8c2a6e131b26476c69b9c5dbf36413e4e3513cce9
+size 1416630

a2c-PandaReachDense-v3/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c37b6e0f19fd7c417c9ea50e8c203c92f6fb1de2fa28943004395dc86a9bfd3a
+size 1180

a2c-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: False
+- 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 0x7e1d838b79a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e1d836c3f40>"}, "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": 1717678889523985754, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 0.48593724  0.41881633  0.8182322 ]\n [ 0.32318288 -0.06420207  0.53251487]\n [ 0.32318288 -0.06420207  0.53251487]\n [ 0.32318288 -0.06420207  0.53251487]]", "desired_goal": "[[ 0.6753942   0.8989489   1.0297809 ]\n [ 0.7468885   0.1281578  -0.5890698 ]\n [ 0.39018017 -0.34852502  0.883982  ]\n [-0.3158677   0.18268321 -1.1175094 ]]", "observation": "[[ 0.48593724  0.41881633  0.8182322   1.2937069   1.922245    1.4677873 ]\n [ 0.32318288 -0.06420207  0.53251487  0.52614737 -0.01287868  0.3685873 ]\n [ 0.32318288 -0.06420207  0.53251487  0.52614737 -0.01287868  0.3685873 ]\n [ 0.32318288 -0.06420207  0.53251487  0.52614737 -0.01287868  0.3685873 ]]"}, "_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": "[[ 4.6467911e-02  2.4478629e-02  2.1392143e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]]", "desired_goal": "[[ 0.05577144  0.08033716  0.2362584 ]\n [ 0.06229192  0.01104843  0.08893096]\n [ 0.02975916 -0.03180202  0.22298962]\n [-0.03463429  0.01594988  0.04083902]]", "observation": "[[ 4.6467911e-02  2.4478629e-02  2.1392143e-01  2.7916941e-01\n   1.1131716e+00  6.8653351e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]]"}, "_episode_num": 302180, "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 0x7e1d837df880>", "add": "<function DictReplayBuffer.add at 0x7e1d837df910>", "sample": "<function DictReplayBuffer.sample at 0x7e1d837df9a0>", "_get_samples": "<function DictReplayBuffer._get_samples at 0x7e1d837dfa30>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e1d837ec440>"}, "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:": "gAWVYAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAwAAAAAAAAABAQGUaAiMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLA4WUjAFDlHSUUpSMDWJvdW5kZWRfYWJvdmWUaBEolgMAAAAAAAAAAQEBlGgVSwOFlGgZdJRSlIwGX3NoYXBllEsDhZSMA2xvd5RoESiWDAAAAAAAAAAAAIC/AACAvwAAgL+UaAtLA4WUaBl0lFKUjARoaWdolGgRKJYMAAAAAAAAAAAAgD8AAIA/AACAP5RoC0sDhZRoGXSUUpSMCGxvd19yZXBylIwELTEuMJSMCWhpZ2hfcmVwcpSMAzEuMJSMCl9ucF9yYW5kb22UjBRudW1weS5yYW5kb20uX3BpY2tsZZSMEF9fZ2VuZXJhdG9yX2N0b3KUk5SMBVBDRzY0lGgyjBRfX2JpdF9nZW5lcmF0b3JfY3RvcpSTlIaUUpR9lCiMDWJpdF9nZW5lcmF0b3KUjAVQQ0c2NJSMBXN0YXRllH2UKGg9ihDl+mJ4X7Ud8MLBboLmhfoZjANpbmOUihDntzp6uS6uIsdbqzCZ8jcldYwKaGFzX3VpbnQzMpRLAIwIdWludGVnZXKUSwB1YnViLg==", "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": "False", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.25.2"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": -0.12428679652512073, "std_reward": 0.10968941474061548, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-06T16:42:42.387509"}

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4b20b2faa356f41222987d51e0182ab3cf82090825a143c04c6c4b175505894
+size 2847