drive that shit

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 0x7b2f1d90b760>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b2f1d90b7f0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b2f1d90b880>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b2f1d90b910>", "_build": "<function ActorCriticPolicy._build at 0x7b2f1d90b9a0>", "forward": "<function ActorCriticPolicy.forward at 0x7b2f1d90ba30>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b2f1d90bac0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b2f1d90bb50>", "_predict": "<function ActorCriticPolicy._predict at 0x7b2f1d90bbe0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b2f1d90bc70>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b2f1d90bd00>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b2f1d90bd90>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b2f24253a00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 131072, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1694988610750501190, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAANtg8L5TW0S5LPkDv10HaDzILKC+wBmVu9sIA7/mubU7bzAOv2hKX7p2qr++myptPBmh4b6t/1e8NL3qvtOGDLzs9uC+LsZKPHR84r5x0ve7Xb8bv96TwDshFCa/WBU7PEidv768dtk81bgev8tE5DeSTxC/xvA6vDKAK79+EvS6lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.3107200000000001, "_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": 40, "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAwAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "3", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

mountain-car-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:700ccc9ca38893a95d8ee94e64cd35594f36ad19fc45da64b72723793e35351d
+size 135464

mountain-car-v0/_stable_baselines3_version

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

mountain-car-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 0x7b2f1d90b760>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b2f1d90b7f0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b2f1d90b880>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b2f1d90b910>",
+        "_build": "<function ActorCriticPolicy._build at 0x7b2f1d90b9a0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7b2f1d90ba30>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b2f1d90bac0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b2f1d90bb50>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7b2f1d90bbe0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b2f1d90bc70>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b2f1d90bd00>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b2f1d90bd90>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7b2f24253a00>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 131072,
+    "_total_timesteps": 100000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1694988610750501190,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAANtg8L5TW0S5LPkDv10HaDzILKC+wBmVu9sIA7/mubU7bzAOv2hKX7p2qr++myptPBmh4b6t/1e8NL3qvtOGDLzs9uC+LsZKPHR84r5x0ve7Xb8bv96TwDshFCa/WBU7PEidv768dtk81bgev8tE5DeSTxC/xvA6vDKAK79+EvS6lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.3107200000000001,
+    "_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": 40,
+    "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAwAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
+        "n": "3",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "n_steps": 2048,
+    "gamma": 0.99,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 10,
+    "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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"
+    }
+}

mountain-car-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad8df02930d55e842d3a9cf3240b14d2c6fce87f183554046a87fa8dad90a12
+size 81273

mountain-car-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0732b0188cd955dc03c350d410e122cdc92b09eed48e20093ff5800c2f37bb02
+size 40001

mountain-car-v0/pytorch_variables.pth

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

mountain-car-v0/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.0.1+cu118
+- GPU Enabled: True
+- Numpy: 1.23.5
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": -200.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-17T22:13:01.224197"}