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: -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 0x7f997703fe20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f997703feb0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f997703ff40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9977048040>", "_build": "<function ActorCriticPolicy._build at 0x7f99770480d0>", "forward": "<function ActorCriticPolicy.forward at 0x7f9977048160>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f99770481f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9977048280>", "_predict": "<function ActorCriticPolicy._predict at 0x7f9977048310>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f99770483a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9977048430>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f99770484c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f9977045180>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 16384, "_total_timesteps": 1000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1713441440168409331, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAL7zB7/DSmc63GcEv5UuLTqkWAK/xMzdOVSu7r5F7CW7Ej0Gv58cWjq13ti+Cze2O1g9Ar+r2P66a+Uhv1+zRbw5Vhm/IioPvNjP+L6oZck7ZwIVvxro4Lo4hRi/ecEDvE9sGr/gfAW8Riwiv1l0qrtothC/THgRO2gnCr+lmfS6lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -15.384, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 4, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True]", "bounded_above": "[ True  True]", "_shape": [2], "low": "[-1.2  -0.07]", "high": "[0.6  0.07]", "low_repr": "[-1.2  -0.07]", "high_repr": "[0.6  0.07]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAwAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "3", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.133.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Thu Oct 5 21:02:42 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.26.2"}}

ppo-MountainCar-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcfa4adf0b59b7ccece346e214b438bae2b77c11fec19e679d905c7a42057f4a
+size 135989

ppo-MountainCar-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+2.0.0a5

ppo-MountainCar-v0/data

@@ -0,0 +1,99 @@
+{
+    "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 0x7f997703fe20>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f997703feb0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f997703ff40>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9977048040>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f99770480d0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f9977048160>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f99770481f0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9977048280>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f9977048310>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f99770483a0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9977048430>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f99770484c0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f9977045180>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 16384,
+    "_total_timesteps": 1000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1713441440168409331,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAL7zB7/DSmc63GcEv5UuLTqkWAK/xMzdOVSu7r5F7CW7Ej0Gv58cWjq13ti+Cze2O1g9Ar+r2P66a+Uhv1+zRbw5Vhm/IioPvNjP+L6oZck7ZwIVvxro4Lo4hRi/ecEDvE9sGr/gfAW8Riwiv1l0qrtothC/THgRO2gnCr+lmfS6lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -15.384,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 4,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_shape": [
+            2
+        ],
+        "low": "[-1.2  -0.07]",
+        "high": "[0.6  0.07]",
+        "low_repr": "[-1.2  -0.07]",
+        "high_repr": "[0.6  0.07]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAwAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
+        "n": "3",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "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,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

ppo-MountainCar-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e77f3640ddbaafa42f12e9baa788622e5cfe04ce909fc0d8854cd86b5515dda
+size 81706

ppo-MountainCar-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5e5e1b8c5176d1401bcfe25383d34511c60d2ff457d37e90ef9c2463c8d3d2b
+size 40434

ppo-MountainCar-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

ppo-MountainCar-v0/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.133.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Thu Oct 5 21:02:42 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.2.1+cu121
+- GPU Enabled: True
+- Numpy: 1.25.2
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.26.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": -200.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-18T11:59:07.377178"}