commit MountainCar model

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 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 0x7f56d48f8280>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f56d48f8310>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f56d48f83a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f56d48f8430>", "_build": "<function ActorCriticPolicy._build at 0x7f56d48f84c0>", "forward": "<function ActorCriticPolicy.forward at 0x7f56d48f8550>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f56d48f85e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f56d48f8670>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f56d48f8700>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f56d48f8790>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f56d48f8820>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f56d48f46c0>"}, "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": 20, "num_timesteps": 1012000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1672234116667488893, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAAOGpAb8AAAAAhywUvwAAAACM9Pa+AAAAAChGGb8AAAAAnJT8vgAAAAAH8Ri/AAAAACnLEr8AAAAAk8kYvwAAAABrVPi+AAAAAK3d974AAAAAqkjgvgAAAADb9f++AAAAANOK+74AAAAAqFfgvgAAAABnrQ6/AAAAAPZkFL8AAAAAO6MVvwAAAABWpAy/AAAAAMRHAL8AAAAAGLHVvgAAAACUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSxRLAoaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYUAAAAAAAAAAEBAQEBAQEBAQEBAQEBAQEBAQEBlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksUhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.01200000000000001, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 150, "n_steps": 2024, "gamma": 0.999, "gae_lambda": 0.94, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 6, "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:dca9da873723f4cb0baf913772810c002a840971939ab7db2aa29aedf74ef37b
+size 134983

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 0x7f56d48f8280>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f56d48f8310>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f56d48f83a0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f56d48f8430>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f56d48f84c0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f56d48f8550>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f56d48f85e0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f56d48f8670>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f56d48f8700>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f56d48f8790>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f56d48f8820>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f56d48f46c0>"
+    },
+    "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": 20,
+    "num_timesteps": 1012000,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1672234116667488893,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAAOGpAb8AAAAAhywUvwAAAACM9Pa+AAAAAChGGb8AAAAAnJT8vgAAAAAH8Ri/AAAAACnLEr8AAAAAk8kYvwAAAABrVPi+AAAAAK3d974AAAAAqkjgvgAAAADb9f++AAAAANOK+74AAAAAqFfgvgAAAABnrQ6/AAAAAPZkFL8AAAAAO6MVvwAAAABWpAy/AAAAAMRHAL8AAAAAGLHVvgAAAACUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSxRLAoaUjAFDlHSUUpQu"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVhwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYUAAAAAAAAAAEBAQEBAQEBAQEBAQEBAQEBAQEBlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksUhZSMAUOUdJRSlC4="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.01200000000000001,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 150,
+    "n_steps": 2024,
+    "gamma": 0.999,
+    "gae_lambda": 0.94,
+    "ent_coef": 0.01,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 6,
+    "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 sha256:7893f41aa295b367eeee7f6ffaa730b4ef0c6b6b1378d4b99920154035726b23
+size 81273

ppo-MountainCar-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42e325470d50696ed18d5d213049ddf57ce1cb66bea9311656d992c776552c0c
+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": -200.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-28T13:40:23.445291"}