Mountain Car firs version

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: -200.00 +/- 0.00
+      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 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 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 ActorCriticPolicy.__init__ at 0x7f840c021670>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f840c021700>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f840c021790>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f840c021820>", "_build": "<function ActorCriticPolicy._build at 0x7f840c0218b0>", "forward": "<function ActorCriticPolicy.forward at 0x7f840c021940>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f840c0219d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f840c021a60>", "_predict": "<function ActorCriticPolicy._predict at 0x7f840c021af0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f840c021b80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f840c021c10>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f840c021ca0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f840c01fb00>"}, "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": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1679208243987788809, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAAZQ4r69zM671jDzvgTF8TpFUwS/Ho5FupjfE7/7Dka8038Mv39RLLtoKQa/FzwJvCG0Lr+YNBo60rUlv0aoR7z0KOu+L6kcOywO977MroY62YABvygA1zsW++a+B3JeOLtG/L6pnc+7xNz/vpGsAbyaAP6+q84lvGMuDb9irfY7lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "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": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.147+-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"}}

ppo-mountain-car.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:290879c09b9fd8bd3b6bd9f460555f4728610f0994cef8ad110af947900c5198
+size 135151

ppo-mountain-car/_stable_baselines3_version

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

ppo-mountain-car/data

@@ -0,0 +1,95 @@
+{
+    "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 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 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 ActorCriticPolicy.__init__ at 0x7f840c021670>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f840c021700>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f840c021790>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f840c021820>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f840c0218b0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f840c021940>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f840c0219d0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f840c021a60>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f840c021af0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f840c021b80>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f840c021c10>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f840c021ca0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f840c01fb00>"
+    },
+    "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": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1679208243987788809,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAAZQ4r69zM671jDzvgTF8TpFUwS/Ho5FupjfE7/7Dka8038Mv39RLLtoKQa/FzwJvCG0Lr+YNBo60rUlv0aoR7z0KOu+L6kcOywO977MroY62YABvygA1zsW++a+B3JeOLtG/L6pnc+7xNz/vpGsAbyaAP6+q84lvGMuDb9irfY7lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.015808000000000044,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 248,
+    "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": 4,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

ppo-mountain-car/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69380f7517c822961dc95915684301d3c2a37d240a8abf6ffac9e9860715a9ac
+size 81273

ppo-mountain-car/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab77462214b564b2c505efb105e3dff3bf861d1d62f36e72848049c4106e5e70
+size 40065

ppo-mountain-car/pytorch_variables.pth

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

ppo-mountain-car/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

results.json

@@ -0,0 +1 @@
+{"mean_reward": -200.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-19T07:39:33.415730"}