Upload agent for MountainCar-v0

.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 0x7f5a64fb45f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f5a64fb4680>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5a64fb4710>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f5a64fb47a0>", "_build": "<function ActorCriticPolicy._build at 0x7f5a64fb4830>", "forward": "<function ActorCriticPolicy.forward at 0x7f5a64fb48c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5a64fb4950>", "_predict": "<function ActorCriticPolicy._predict at 0x7f5a64fb49e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5a64fb4a70>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f5a64fb4b00>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5a64fb4b90>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f5a65008300>"}, "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": 1653519185.482661, "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/////0sAdJRiiUOAb/ftvhcL/rrZ5M++9iD/un9dCL9rRwU8skPivpsaRDttK+S+avYvu+gJ+L6CBHo4hKjNvmTa+ztHLba+jCFru3QvFb/cUsA7sj0Uv00T8TrVG+++c0vXO6i93743ycQ6hZHovnhNKDyuyCm/5gxnO0UpIb8m0v86SZMGv8tqoLuUdJRiLg=="}, "_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": "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:c9844742c262e17ecbb82bc51bf8c95d06b841fd5dcffc0d56ff98866f574bfd
+size 131873

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 0x7f5a64fb45f0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f5a64fb4680>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5a64fb4710>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f5a64fb47a0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f5a64fb4830>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f5a64fb48c0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5a64fb4950>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f5a64fb49e0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5a64fb4a70>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f5a64fb4b00>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5a64fb4b90>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f5a65008300>"
+    },
+    "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": 1653519185.482661,
+    "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/////0sAdJRiiUOAb/ftvhcL/rrZ5M++9iD/un9dCL9rRwU8skPivpsaRDttK+S+avYvu+gJ+L6CBHo4hKjNvmTa+ztHLba+jCFru3QvFb/cUsA7sj0Uv00T8TrVG+++c0vXO6i93743ycQ6hZHovnhNKDyuyCm/5gxnO0UpIb8m0v86SZMGv8tqoLuUdJRiLg=="
+    },
+    "_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 sha256:4d38e50d96140a489b73e20732806187ce75c579de0632cd91974c54ff11dc45
+size 78173

ppo-MountainCar-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e137b8301cf263e87275e595a5ba1183d48eed8bffcb39c98166966d3b4ea068
+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-5.4.188+-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: True
+Numpy: 1.21.6
+Gym: 0.21.0

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43ae0e30c15089bd7631ae3c0155d91bda62e33b1a16809e8065ac016131a914
+size 169233

results.json

@@ -0,0 +1 @@
+{"mean_reward": -200.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-25T23:00:15.319171"}