Initial commit

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- PandaReachDense-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: A2C
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: PandaReachDense-v2
+      type: PandaReachDense-v2
+    metrics:
+    - type: mean_reward
+      value: -20.70 +/- 8.74
+      name: mean_reward
+      verified: false
+---
+
+# **A2C** Agent playing **PandaReachDense-v2**
+This is a trained model of a **A2C** agent playing **PandaReachDense-v2**
+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-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da652df913da1de293aa2ced402d25e7972e9aecc65ad617770503517f83f3e4
+size 103529

a2c-PandaReachDense-v2/_stable_baselines3_version

@@ -0,0 +1 @@
+1.8.0

a2c-PandaReachDense-v2/data

@@ -0,0 +1,95 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=",
+        "__module__": "stable_baselines3.common.policies",
+        "__doc__": "\n    MultiInputActorClass 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 (Tuple)\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 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: Uses the CombinedExtractor\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 MultiInputActorCriticPolicy.__init__ at 0x7a0a1a55c3a0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7a0a1a54abc0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=",
+        "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>",
+        "optimizer_kwargs": {
+            "alpha": 0.99,
+            "eps": 1e-05,
+            "weight_decay": 0
+        }
+    },
+    "num_timesteps": 1000,
+    "_total_timesteps": 1000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1690639716632644887,
+    "learning_rate": 0.0007,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'collections.OrderedDict'>",
+        ":serialized:": "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",
+        "achieved_goal": "[[0.6149996  0.00757062 0.73171467]\n [0.6149996  0.00757062 0.73171467]\n [0.6149996  0.00757062 0.73171467]\n [0.6149996  0.00757062 0.73171467]]",
+        "desired_goal": "[[-0.8941896   0.9561309   1.0644481 ]\n [-0.66405857 -1.6926495   1.2835476 ]\n [ 1.0973053  -0.40604728  0.35091385]\n [ 0.21623985 -0.06085005  0.5143035 ]]",
+        "observation": "[[ 0.6149996   0.00757062  0.73171467  0.07669397 -0.00378776  0.0448415 ]\n [ 0.6149996   0.00757062  0.73171467  0.07669397 -0.00378776  0.0448415 ]\n [ 0.6149996   0.00757062  0.73171467  0.07669397 -0.00378776  0.0448415 ]\n [ 0.6149996   0.00757062  0.73171467  0.07669397 -0.00378776  0.0448415 ]]"
+    },
+    "_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": "[[ 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]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]]",
+        "desired_goal": "[[-0.0928089   0.01297703  0.05055067]\n [-0.14057235  0.03577578  0.19299826]\n [-0.02665169  0.09828089  0.06715418]\n [ 0.07564206  0.0661465   0.06334393]]",
+        "observation": "[[ 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]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]]"
+    },
+    "_episode_num": 0,
+    "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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 50,
+    "n_steps": 5,
+    "gamma": 0.99,
+    "gae_lambda": 1.0,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "normalize_advantage": false,
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.dict.Dict'>",
+        ":serialized:": "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",
+        "spaces": "OrderedDict([('achieved_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('desired_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('observation', Box([-10. -10. -10. -10. -10. -10.], [10. 10. 10. 10. 10. 10.], (6,), float32))])",
+        "_shape": null,
+        "dtype": null,
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            3
+        ],
+        "low": "[-1. -1. -1.]",
+        "high": "[1. 1. 1.]",
+        "bounded_below": "[ True  True  True]",
+        "bounded_above": "[ True  True  True]",
+        "_np_random": null
+    },
+    "n_envs": 4
+}

a2c-PandaReachDense-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd1868df99619508b748518beaaa91004f2791a52d802d66e44287e062f2aec2
+size 44606

a2c-PandaReachDense-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2a2f09073beaec467077d462c95a0c6b6a0561a2826ec2507de896a2f0a96f6
+size 45886

a2c-PandaReachDense-v2/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

a2c-PandaReachDense-v2/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023
+- Python: 3.10.6
+- Stable-Baselines3: 1.8.0
+- PyTorch: 2.0.1+cu118
+- GPU Enabled: False
+- Numpy: 1.22.4
+- Gym: 0.21.0

config.json

@@ -0,0 +1 @@
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    MultiInputActorClass 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 (Tuple)\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 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: Uses the CombinedExtractor\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 MultiInputActorCriticPolicy.__init__ at 0x7a0a1a55c3a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7a0a1a54abc0>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 1000, "_total_timesteps": 1000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1690639716632644887, "learning_rate": 0.0007, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[0.6149996  0.00757062 0.73171467]\n [0.6149996  0.00757062 0.73171467]\n [0.6149996  0.00757062 0.73171467]\n [0.6149996  0.00757062 0.73171467]]", "desired_goal": "[[-0.8941896   0.9561309   1.0644481 ]\n [-0.66405857 -1.6926495   1.2835476 ]\n [ 1.0973053  -0.40604728  0.35091385]\n [ 0.21623985 -0.06085005  0.5143035 ]]", "observation": "[[ 0.6149996   0.00757062  0.73171467  0.07669397 -0.00378776  0.0448415 ]\n [ 0.6149996   0.00757062  0.73171467  0.07669397 -0.00378776  0.0448415 ]\n [ 0.6149996   0.00757062  0.73171467  0.07669397 -0.00378776  0.0448415 ]\n [ 0.6149996   0.00757062  0.73171467  0.07669397 -0.00378776  0.0448415 ]]"}, "_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": "[[ 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]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]]", "desired_goal": "[[-0.0928089   0.01297703  0.05055067]\n [-0.14057235  0.03577578  0.19299826]\n [-0.02665169  0.09828089  0.06715418]\n [ 0.07564206  0.0661465   0.06334393]]", "observation": "[[ 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]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]]"}, "_episode_num": 0, "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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 50, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "normalize_advantage": false, "observation_space": {":type:": "<class 'gym.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('desired_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('observation', Box([-10. -10. -10. -10. -10. -10.], [10. 10. 10. 10. 10. 10.], (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "bounded_below": "[ True  True  True]", "bounded_above": "[ True  True  True]", "_np_random": null}, "n_envs": 4, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.6", "Stable-Baselines3": "1.8.0", "PyTorch": "2.0.1+cu118", "GPU Enabled": "False", "Numpy": "1.22.4", "Gym": "0.21.0"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": -20.69652513638139, "std_reward": 8.738878137938533, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-29T14:10:26.197624"}

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d71cb71e813e2c076b7b198e315e1cdd57a3f3b6c42982afeaf4ef665891251
+size 2387