Upload PandaReachDense-v2 A2C model 200K

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: -8.83 +/- 2.70
+      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:a95fa134feec9d7012d46b6a807f4d2eb3608bd7a94eb587c3468f502eefa5d0
+size 104827

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:": "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 0x7f17b907daf0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f17b9081100>"
+    },
+    "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": 2164,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1679320712998165492,
+    "learning_rate": 0.0007,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOS9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOS9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/RvAGjbi6x4WUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
+    },
+    "_last_obs": {
+        ":type:": "<class 'collections.OrderedDict'>",
+        ":serialized:": "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",
+        "achieved_goal": "[[ 0.99227834 -0.44972032 -0.8899054 ]\n [ 1.506882    1.6923558   0.22662584]\n [ 1.1683768   0.30878985 -0.18672095]\n [-1.1585605  -1.3554838   0.01671157]]",
+        "desired_goal": "[[-0.1354499  -0.40909132 -1.3561041 ]\n [ 1.2725149   0.68552125 -1.3635778 ]\n [ 0.35823503 -1.0290644  -1.4775001 ]\n [ 1.2331864   1.3948036   0.03104856]]",
+        "observation": "[[ 0.99227834 -0.44972032 -0.8899054  -0.70487505 -0.04856179  0.06866235]\n [ 1.506882    1.6923558   0.22662584 -1.0940096   1.1262611  -2.205987  ]\n [ 1.1683768   0.30878985 -0.18672095  2.557246    0.3044851  -0.05491566]\n [-1.1585605  -1.3554838   0.01671157 -2.6452594  -1.5291537  -1.6680303 ]]"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": "[[-0.10539735 -0.04838578  0.20518143]\n [-0.0969891  -0.06594792  0.07817443]\n [ 0.05280672 -0.08013167  0.02493426]\n [ 0.02422679  0.13808827  0.28032807]]",
+        "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": 0.99784,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 108,
+    "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 sha256:3c580f18305063f05f710c1f71d7b0bfead70c1d452346b3c0860345cdea1e98
+size 44734

a2c-PandaReachDense-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0065b18311de2ba4403532d4a1fcfd5e0ee1d16c358e0d9304e8ff71e717657
+size 46014

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-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
+- Python: 3.9.16
+- Stable-Baselines3: 1.7.0
+- PyTorch: 1.13.1+cu116
+- GPU Enabled: True
+- 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 0x7f17b907daf0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f17b9081100>"}, "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:": "gAWVbQEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLA4WUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWDAAAAAAAAAAAAIC/AACAvwAAgL+UaApLA4WUjAFDlHSUUpSMBGhpZ2iUaBIolgwAAAAAAAAAAACAPwAAgD8AAIA/lGgKSwOFlGgVdJRSlIwNYm91bmRlZF9iZWxvd5RoEiiWAwAAAAAAAAABAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLA4WUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYDAAAAAAAAAAEBAZRoIUsDhZRoFXSUUpSMCl9ucF9yYW5kb22UTnViLg==", "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": 2164, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1679320712998165492, "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": "[[ 0.99227834 -0.44972032 -0.8899054 ]\n [ 1.506882    1.6923558   0.22662584]\n [ 1.1683768   0.30878985 -0.18672095]\n [-1.1585605  -1.3554838   0.01671157]]", "desired_goal": "[[-0.1354499  -0.40909132 -1.3561041 ]\n [ 1.2725149   0.68552125 -1.3635778 ]\n [ 0.35823503 -1.0290644  -1.4775001 ]\n [ 1.2331864   1.3948036   0.03104856]]", "observation": "[[ 0.99227834 -0.44972032 -0.8899054  -0.70487505 -0.04856179  0.06866235]\n [ 1.506882    1.6923558   0.22662584 -1.0940096   1.1262611  -2.205987  ]\n [ 1.1683768   0.30878985 -0.18672095  2.557246    0.3044851  -0.05491566]\n [-1.1585605  -1.3554838   0.01671157 -2.6452594  -1.5291537  -1.6680303 ]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": "[[-0.10539735 -0.04838578  0.20518143]\n [-0.0969891  -0.06594792  0.07817443]\n [ 0.05280672 -0.08013167  0.02493426]\n [ 0.02422679  0.13808827  0.28032807]]", "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": 0.99784, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 108, "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-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": -8.82700487487018, "std_reward": 2.7018176860092185, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-20T13:58:44.677790"}

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03508c7a92e43b6dfdf0da1b4e086664177d2ebfca0e2e8c795877e6e1e02353
+size 3056