commit a2c-PandaReachDense-v2

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: -11.17 +/- 3.25
+      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:b211e0ce70bfc230521852092a21acea69dc028c009c20dcc9b57e8a855cdcf2
+size 103718

a2c-PandaReachDense-v2/_stable_baselines3_version

@@ -0,0 +1 @@
+1.7.0

a2c-PandaReachDense-v2/data

@@ -0,0 +1,94 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gASVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=",
+        "__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 0x79ea20fede60>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x79ea20fccf00>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gASVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/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,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1680812870737837029,
+    "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": "[[0.71737295 0.01751485 1.9057084 ]\n [0.71737295 0.01751485 1.9057084 ]\n [0.71737295 0.01751485 1.9057084 ]\n [0.71737295 0.01751485 1.9057084 ]]",
+        "desired_goal": "[[ 1.045626   -1.237713    0.55173796]\n [ 0.64519787 -0.9604759   0.89997333]\n [ 0.98640054  1.6677494   0.6017811 ]\n [-0.9173563   0.9254372  -1.6059502 ]]",
+        "observation": "[[0.71737295 0.01751485 1.9057084  0.12724838 0.00878435 0.09295581]\n [0.71737295 0.01751485 1.9057084  0.12724838 0.00878435 0.09295581]\n [0.71737295 0.01751485 1.9057084  0.12724838 0.00878435 0.09295581]\n [0.71737295 0.01751485 1.9057084  0.12724838 0.00878435 0.09295581]]"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVjAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwSFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDBAEBAQGUdJRiLg=="
+    },
+    "_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": "[[-0.0439516  -0.11985926  0.12383612]\n [-0.07689843  0.0494895   0.12406432]\n [ 0.12849343  0.08257522  0.2240277 ]\n [-0.00093305 -0.10907969  0.2734778 ]]",
+        "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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_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:a9792d1d2b7517e858ab589b134e43da1c073ba51afdbd718235c61901c82ab2
+size 44606

a2c-PandaReachDense-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc96dfc549df35278c75a32ed020969762bae5c18edda0e5ccd8982800277117
+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-5.15.90+-x86_64-with-debian-bullseye-sid # 1 SMP Sat Mar 25 11:28:03 UTC 2023
+- Python: 3.7.12
+- Stable-Baselines3: 1.7.0
+- PyTorch: 1.13.0+cpu
+- GPU Enabled: False
+- Numpy: 1.21.6
+- Gym: 0.21.0

config.json

@@ -0,0 +1 @@
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=", "__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 0x79ea20fede60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x79ea20fccf00>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gASVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/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, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1680812870737837029, "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": "[[0.71737295 0.01751485 1.9057084 ]\n [0.71737295 0.01751485 1.9057084 ]\n [0.71737295 0.01751485 1.9057084 ]\n [0.71737295 0.01751485 1.9057084 ]]", "desired_goal": "[[ 1.045626   -1.237713    0.55173796]\n [ 0.64519787 -0.9604759   0.89997333]\n [ 0.98640054  1.6677494   0.6017811 ]\n [-0.9173563   0.9254372  -1.6059502 ]]", "observation": "[[0.71737295 0.01751485 1.9057084  0.12724838 0.00878435 0.09295581]\n [0.71737295 0.01751485 1.9057084  0.12724838 0.00878435 0.09295581]\n [0.71737295 0.01751485 1.9057084  0.12724838 0.00878435 0.09295581]\n [0.71737295 0.01751485 1.9057084  0.12724838 0.00878435 0.09295581]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASVjAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwSFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDBAEBAQGUdJRiLg=="}, "_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": "[[-0.0439516  -0.11985926  0.12383612]\n [-0.07689843  0.0494895   0.12406432]\n [ 0.12849343  0.08257522  0.2240277 ]\n [-0.00093305 -0.10907969  0.2734778 ]]", "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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_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": "Linux-5.15.90+-x86_64-with-debian-bullseye-sid # 1 SMP Sat Mar 25 11:28:03 UTC 2023", "Python": "3.7.12", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.0+cpu", "GPU Enabled": "False", "Numpy": "1.21.6", "Gym": "0.21.0"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": -11.169907528348267, "std_reward": 3.253848068539077, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-06T20:27:58.314301"}

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d21b25afe84259fb44442f0dac294f6837f0ff2c0163c84b33addb3143c855a
+size 3731