Upload PPO MountainCar-v0 trained agent

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- MountainCar-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: MountainCar-v0
+      type: MountainCar-v0
+    metrics:
+    - type: mean_reward
+      value: -128.30 +/- 24.10
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **MountainCar-v0**
+This is a trained model of a **PPO** agent playing **MountainCar-v0**
+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
+
+...
+```

config.json

@@ -0,0 +1 @@
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    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\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: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features 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 ActorCriticPolicy.__init__ at 0x7f2b2b472280>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2b2b472310>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2b2b4723a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2b2b472430>", "_build": "<function ActorCriticPolicy._build at 0x7f2b2b4724c0>", "forward": "<function ActorCriticPolicy.forward at 0x7f2b2b472550>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2b2b4725e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f2b2b472670>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2b2b472700>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2b2b472790>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2b2b472820>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f2b2b46acc0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVYwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAACamZm/KVyPvZRoCksChZSMAUOUdJRSlIwEaGlnaJRoEiiWCAAAAAAAAACamRk/KVyPPZRoCksChZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolgIAAAAAAAAAAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAoWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYCAAAAAAAAAAEBlGghSwKFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu", "dtype": "float32", "_shape": [2], "low": "[-1.2  -0.07]", "high": "[0.6  0.07]", "bounded_below": "[ True  True]", "bounded_above": "[ True  True]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLA4wGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 3, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 5013504, "_total_timesteps": 5000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1671214893121374875, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAF9Bur7ZBTU8DNKZvSonP728206+ZtitO7nLCb+gcIq8uNljv+Nzzbysxo6/QIoBvA8TWr6jJ9W6fhqXv64IIDwNWY+/l3AuO45Wl78SWI+7tJQBv8CQLLtX0Cm/VKQcvUjuoD34ouw6yITqvgAAAAD+BYs+Tw8nPR3xQj529FM9lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAABAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0027007999999999477, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 612, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 2, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

ppo-MountainCar-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a35cf90e1b857c28065743fc34de03ec35dcf09d7c6fca3414325f413ee4b80
+size 134941

ppo-MountainCar-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+1.6.2

ppo-MountainCar-v0/data

@@ -0,0 +1,94 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
+        "__module__": "stable_baselines3.common.policies",
+        "__doc__": "\n    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\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: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features 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 ActorCriticPolicy.__init__ at 0x7f2b2b472280>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2b2b472310>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2b2b4723a0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2b2b472430>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f2b2b4724c0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f2b2b472550>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2b2b4725e0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f2b2b472670>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2b2b472700>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2b2b472790>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2b2b472820>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f2b2b46acc0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gAWVYwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAACamZm/KVyPvZRoCksChZSMAUOUdJRSlIwEaGlnaJRoEiiWCAAAAAAAAACamRk/KVyPPZRoCksChZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolgIAAAAAAAAAAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAoWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYCAAAAAAAAAAEBlGghSwKFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu",
+        "dtype": "float32",
+        "_shape": [
+            2
+        ],
+        "low": "[-1.2  -0.07]",
+        "high": "[0.6  0.07]",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLA4wGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 3,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "num_timesteps": 5013504,
+    "_total_timesteps": 5000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1671214893121374875,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAF9Bur7ZBTU8DNKZvSonP728206+ZtitO7nLCb+gcIq8uNljv+Nzzbysxo6/QIoBvA8TWr6jJ9W6fhqXv64IIDwNWY+/l3AuO45Wl78SWI+7tJQBv8CQLLtX0Cm/VKQcvUjuoD34ouw6yITqvgAAAAD+BYs+Tw8nPR3xQj529FM9lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAABAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.0027007999999999477,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 612,
+    "n_steps": 1024,
+    "gamma": 0.999,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.01,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 2,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

ppo-MountainCar-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37004d01256f8159b17e436c43790ca6e4e94e5f16d46e032f360bb45941ad81
+size 81273

ppo-MountainCar-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f64d76148ef055831d837872d1a8e9d83548a9f68b21c3047131dff03a5bfcc
+size 39873

ppo-MountainCar-v0/pytorch_variables.pth

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

ppo-MountainCar-v0/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
+Python: 3.8.16
+Stable-Baselines3: 1.6.2
+PyTorch: 1.13.0+cu116
+GPU Enabled: True
+Numpy: 1.21.6
+Gym: 0.21.0

results.json

@@ -0,0 +1 @@
+{"mean_reward": -128.3, "std_reward": 24.095850265139017, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-16T18:43:48.064235"}