boooom!

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: -10.68 +/- 1.72
+      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 sha256:7e139265f1bd33b339a05eb44bf5b90a13640160d0a6d5d942ab2ccfb02730b3
+size 102891

a2c-PandaReachDense-v2/_stable_baselines3_version

@@ -0,0 +1 @@
+1.3.0

a2c-PandaReachDense-v2/data

@@ -0,0 +1,93 @@
+{
+    "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 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: Uses the CombinedExtractor\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the feature 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 MultiInputActorCriticPolicy.__init__ at 0x000002660679A940>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x000002660679B940>"
+    },
+    "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
+        }
+    },
+    "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,
+    "num_timesteps": 1000,
+    "_total_timesteps": 1000,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1688884529.7172375,
+    "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": "[[ 0.6228766  -0.04017196  1.5559772 ]\n [ 0.6228766  -0.04017196  1.5559772 ]\n [ 0.6228766  -0.04017196  1.5559772 ]\n [ 0.6228766  -0.04017196  1.5559772 ]]",
+        "desired_goal": "[[ 0.95066285  0.16185108  1.3020294 ]\n [-1.1635678  -1.0314251   0.11337549]\n [-1.7373382  -1.0354726  -1.2038316 ]\n [-0.30889267  1.7113497   1.3439573 ]]",
+        "observation": "[[ 0.6228766  -0.04017196  1.5559772   0.07485413 -0.01958985  0.10787753]\n [ 0.6228766  -0.04017196  1.5559772   0.07485413 -0.01958985  0.10787753]\n [ 0.6228766  -0.04017196  1.5559772   0.07485413 -0.01958985  0.10787753]\n [ 0.6228766  -0.04017196  1.5559772   0.07485413 -0.01958985  0.10787753]]"
+    },
+    "_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": "[[ 0.04011713  0.13230608  0.28109518]\n [ 0.06698749  0.0548093   0.11737117]\n [ 0.09167696 -0.13051982  0.22220634]\n [ 0.08915178 -0.09786659  0.20898262]]",
+        "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,
+    "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
+}

a2c-PandaReachDense-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42f4b82e141cf75f3fc44be066a5afa19be5da6f95db5e341c6bc3bb8f46cf3f
+size 44606

a2c-PandaReachDense-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d6ae3e93257c87be0605552d9cdff9de4a8fdaa7020c2edd8355f8e03c50b7f
+size 45374

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: Windows-10-10.0.22621-SP0 10.0.22621
+Python: 3.9.13
+Stable-Baselines3: 1.3.0
+PyTorch: 2.0.1+cpu
+GPU Enabled: False
+Numpy: 1.25.1
+Gym: 0.19.0

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 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: Uses the CombinedExtractor\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the feature 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 MultiInputActorCriticPolicy.__init__ at 0x000002660679A940>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000002660679B940>"}, "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}}, "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, "num_timesteps": 1000, "_total_timesteps": 1000, "seed": null, "action_noise": null, "start_time": 1688884529.7172375, "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": "[[ 0.6228766  -0.04017196  1.5559772 ]\n [ 0.6228766  -0.04017196  1.5559772 ]\n [ 0.6228766  -0.04017196  1.5559772 ]\n [ 0.6228766  -0.04017196  1.5559772 ]]", "desired_goal": "[[ 0.95066285  0.16185108  1.3020294 ]\n [-1.1635678  -1.0314251   0.11337549]\n [-1.7373382  -1.0354726  -1.2038316 ]\n [-0.30889267  1.7113497   1.3439573 ]]", "observation": "[[ 0.6228766  -0.04017196  1.5559772   0.07485413 -0.01958985  0.10787753]\n [ 0.6228766  -0.04017196  1.5559772   0.07485413 -0.01958985  0.10787753]\n [ 0.6228766  -0.04017196  1.5559772   0.07485413 -0.01958985  0.10787753]\n [ 0.6228766  -0.04017196  1.5559772   0.07485413 -0.01958985  0.10787753]]"}, "_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": "[[ 0.04011713  0.13230608  0.28109518]\n [ 0.06698749  0.0548093   0.11737117]\n [ 0.09167696 -0.13051982  0.22220634]\n [ 0.08915178 -0.09786659  0.20898262]]", "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, "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, "system_info": {"OS": "Windows-10-10.0.22621-SP0 10.0.22621", "Python": "3.9.13", "Stable-Baselines3": "1.3.0", "PyTorch": "2.0.1+cpu", "GPU Enabled": "False", "Numpy": "1.25.1", "Gym": "0.19.0"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": -10.683975160121918, "std_reward": 1.7211206244902828, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-08T23:35:33.817607"}

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:992694e3428fb8178c69caae02651fadee2a1e8d145440b18704caf4c74b35e0
+size 3056