Upload PPO MountainCar-v0 trained agent

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,36 @@
+---
+library_name: stable-baselines3
+tags:
+- MountainCar-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: -200.00 +/- 0.00
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: MountainCar-v0
+      type: MountainCar-v0
+---
+
+# **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:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7fcdcefaeb00>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcdcefaeb90>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcdcefaec20>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcdcefaecb0>", "_build": "<function ActorCriticPolicy._build at 0x7fcdcefaed40>", "forward": "<function ActorCriticPolicy.forward at 0x7fcdcefaedd0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcdcefaee60>", "_predict": "<function ActorCriticPolicy._predict at 0x7fcdcefaeef0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcdcefaef80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcdcefb2050>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcdcefb20e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fcdcefff840>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "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:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLA4wGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 3, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1653574172.9784727, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASVCgEAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxBLAoaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUOANrzivheuwTs3BSi/RTreOsjMu77Ju0u7+Hwdvxo/PblyjRm/gfCSu+qyDL9YwrG7dwPEvjev+LsV0b2+ctS0u52wvr7NuXo6Ryz2vmZjbDwkJiK/rGEeujh+EL86Fx87X/cMv/SNVjxR+O6+dF0LupvIyb5fMTM7WuUCv5URYruUdJRiLg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="}, "_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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 124, "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-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "False", "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:eca7b71f5e6d8bb261ad637e8cff60413b920b80c9194ee95958fbd6ea198ed4
+size 131491

ppo-MountainCar-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.0

ppo-MountainCar-v0/data

@@ -0,0 +1,94 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
+        "__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 0x7fcdcefaeb00>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcdcefaeb90>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcdcefaec20>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcdcefaecb0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fcdcefaed40>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fcdcefaedd0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcdcefaee60>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fcdcefaeef0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcdcefaef80>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcdcefb2050>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcdcefb20e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fcdcefff840>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "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:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLA4wGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 3,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "num_timesteps": 507904,
+    "_total_timesteps": 500000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1653574172.9784727,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVCgEAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxBLAoaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUOANrzivheuwTs3BSi/RTreOsjMu77Ju0u7+Hwdvxo/PblyjRm/gfCSu+qyDL9YwrG7dwPEvjev+LsV0b2+ctS0u52wvr7NuXo6Ryz2vmZjbDwkJiK/rGEeujh+EL86Fx87X/cMv/SNVjxR+O6+dF0LupvIyb5fMTM7WuUCv5URYruUdJRiLg=="
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="
+    },
+    "_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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 124,
+    "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-MountainCar-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ef8d05a440a8073a382666dc1de7b43a038a50c586818e03156cfa449ca204b
+size 77917

ppo-MountainCar-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1bff70505701f49d151916b55296ff73fbeb84cc3e6cb44f7062822dadb24f5
+size 39745

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-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
+Python: 3.7.13
+Stable-Baselines3: 1.5.0
+PyTorch: 1.11.0+cu113
+GPU Enabled: False
+Numpy: 1.21.6
+Gym: 0.21.0

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e539080018545ca1d23d8fe63cf28e1646fd0814c04f946026ee909af911899
+size 214630

results.json

@@ -0,0 +1 @@
+{"mean_reward": -200.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-26T14:17:27.964115"}