Upload PPO Acrobot-v1 trained agent

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- Acrobot-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Acrobot-v1
+      type: Acrobot-v1
+    metrics:
+    - type: mean_reward
+      value: -83.00 +/- 8.27
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **Acrobot-v1**
+This is a trained model of a **PPO** agent playing **Acrobot-v1**
+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 0x7ddddfd2dc60>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ddddfd2dcf0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ddddfd2dd80>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ddddfd2de10>", "_build": "<function ActorCriticPolicy._build at 0x7ddddfd2dea0>", "forward": "<function ActorCriticPolicy.forward at 0x7ddddfd2df30>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ddddfd2dfc0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ddddfd2e050>", "_predict": "<function ActorCriticPolicy._predict at 0x7ddddfd2e0e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ddddfd2e170>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ddddfd2e200>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ddddfd2e290>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ddddfec2440>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1708362910823365907, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_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": -0.015808000000000044, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwFpAAAAAAACMAWyUS2qMAXSUR0B9Rl4GD+R6dX2UKGgGR8BRgAAAAAAAaAdLR2gIR0B9RrLW7OE/dX2UKGgGR8BVQAAAAAAAaAdLVmgIR0B9RuteUpuudX2UKGgGR8BRwAAAAAAAaAdLSGgIR0B9R48/2TPjdX2UKGgGR8BTgAAAAAAAaAdLT2gIR0B9R2v/zasZdX2UKGgGR8BWgAAAAAAAaAdLW2gIR0B9R9MIu5BkdX2UKGgGR8BWAAAAAAAAaAdLWWgIR0B9SAAWBSUDdX2UKGgGR8BZQAAAAAAAaAdLZmgIR0B9SISGrS3LdX2UKGgGR8BWQAAAAAAAaAdLWmgIR0B9SLIq9XcQdX2UKGgGR8BTQAAAAAAAaAdLTmgIR0B9SK/h2nsLdX2UKGgGR8BWgAAAAAAAaAdLW2gIR0B9SR7Y02tMdX2UKGgGR8BUQAAAAAAAaAdLUmgIR0B9SVv73wkPdX2UKGgGR8BTgAAAAAAAaAdLT2gIR0B9SZFb3XZodX2UKGgGR8BUAAAAAAAAaAdLUWgIR0B9Sb4REnb7dX2UKGgGR8BVQAAAAAAAaAdLVmgIR0B9SeMxXXAedX2UKGgGR8BSQAAAAAAAaAdLSmgIR0B9ShZeRgZ1dX2UKGgGR8BXAAAAAAAAaAdLXWgIR0B9SpY+0PYndX2UKGgGR8BPgAAAAAAAaAdLQGgIR0B9SqaBqbjMdX2UKGgGR8BTQAAAAAAAaAdLTmgIR0B9SuA8SwnqdX2UKGgGR8BVAAAAAAAAaAdLVWgIR0B9SwcFQl8gdX2UKGgGR8BRwAAAAAAAaAdLSGgIR0B9SzfgrH2idX2UKGgGR8BQAAAAAAAAaAdLQWgIR0B9S/xBmf5DdX2UKGgGR8BUAAAAAAAAaAdLUWgIR0B9TAjX4CZGdX2UKGgGR8BUwAAAAAAAaAdLVGgIR0B9TF+6RQrMdX2UKGgGR8BTQAAAAAAAaAdLTmgIR0B9TMbbUPQOdX2UKGgGR8BTQAAAAAAAaAdLTmgIR0B9TMSUTtb+dX2UKGgGR8BTQAAAAAAAaAdLTmgIR0B9TSLWI42kdX2UKGgGR8BTQAAAAAAAaAdLTmgIR0B9TV8+iaiLdX2UKGgGR8BRwAAAAAAAaAdLSGgIR0B9TUlJHy3DdX2UKGgGR8BQAAAAAAAAaAdLQWgIR0B9TTf1pTMrdX2UKGgGR8BTwAAAAAAAaAdLUGgIR0B9Tdle4TbndX2UKGgGR8BRgAAAAAAAaAdLR2gIR0B9TiTzND+jdX2UKGgGR8BPAAAAAAAAaAdLP2gIR0B9TlXIU8FIdX2UKGgGR8BRwAAAAAAAaAdLSGgIR0B9Tj0RODaodX2UKGgGR8BVQAAAAAAAaAdLVmgIR0B9TmvUz9CNdX2UKGgGR8BVAAAAAAAAaAdLVWgIR0B9TzeSB9ThdX2UKGgGR8BWAAAAAAAAaAdLWWgIR0B9T5tO2y9mdX2UKGgGR8BWQAAAAAAAaAdLWmgIR0B9UJImPYFrdX2UKGgGR8BSQAAAAAAAaAdLSmgIR0B9UJ9srNGFdX2UKGgGR8BWQAAAAAAAaAdLWmgIR0B9UKQ3gk1NdX2UKGgGR8BVwAAAAAAAaAdLWGgIR0B9UURGtp22dX2UKGgGR8BXAAAAAAAAaAdLXWgIR0B9URnM+u/2dX2UKGgGR8BTAAAAAAAAaAdLTWgIR0B9UV+Vkc0cdX2UKGgGR8BUQAAAAAAAaAdLUmgIR0B9UWSOinHedX2UKGgGR8BSAAAAAAAAaAdLSWgIR0B9UaimEXchdX2UKGgGR8BUQAAAAAAAaAdLUmgIR0B9UYl6Z6UrdX2UKGgGR8BPgAAAAAAAaAdLQGgIR0B9Ubhl18sudX2UKGgGR8BRQAAAAAAAaAdLRmgIR0B9Uhvze40/dX2UKGgGR8BSAAAAAAAAaAdLSWgIR0B9UhKGtZFHdX2UKGgGR8BZQAAAAAAAaAdLZmgIR0B9Um5NGmUGdX2UKGgGR8BRwAAAAAAAaAdLSGgIR0B9UtWtEG7jdX2UKGgGR8BWQAAAAAAAaAdLWmgIR0B9UsS26TW5dX2UKGgGR8BTQAAAAAAAaAdLTmgIR0B9U3a6BiCrdX2UKGgGR8BTgAAAAAAAaAdLT2gIR0B9VG5y2hIwdX2UKGgGR8BUwAAAAAAAaAdLVGgIR0B9VKilBQendX2UKGgGR8BWQAAAAAAAaAdLWmgIR0B9VOqHXVbzdX2UKGgGR8BTQAAAAAAAaAdLTmgIR0B9VQphF3INdX2UKGgGR8BSQAAAAAAAaAdLSmgIR0B9VPTTfBN3dX2UKGgGR8BUAAAAAAAAaAdLUWgIR0B9VQQsf7rLdX2UKGgGR8BUAAAAAAAAaAdLUWgIR0B9VUk0Jng6dX2UKGgGR8BUAAAAAAAAaAdLUWgIR0B9VYxtYSxrdX2UKGgGR8BUAAAAAAAAaAdLUWgIR0B9VZtYSxqxdX2UKGgGR8BSAAAAAAAAaAdLSWgIR0B9VZoQFs55dX2UKGgGR8BSAAAAAAAAaAdLSWgIR0B9VZClabF1dX2UKGgGR8BWgAAAAAAAaAdLW2gIR0B9VekZaV2SdX2UKGgGR8BSQAAAAAAAaAdLSmgIR0B9VlQpF1B/dX2UKGgGR8BSwAAAAAAAaAdLTGgIR0B9Vn3IuGsWdX2UKGgGR8BRQAAAAAAAaAdLRmgIR0B9Vs+1SflIdX2UKGgGR8BXgAAAAAAAaAdLX2gIR0B9VvY150KadX2UKGgGR8BOgAAAAAAAaAdLPmgIR0B9V2hPCVKPdX2UKGgGR8BOgAAAAAAAaAdLPmgIR0B9V6PU8V59dX2UKGgGR8BPgAAAAAAAaAdLQGgIR0B9WLPKMefadX2UKGgGR8BTgAAAAAAAaAdLT2gIR0B9WMfRu0kXdX2UKGgGR8BTAAAAAAAAaAdLTWgIR0B9WQRe1KGtdX2UKGgGR8BTgAAAAAAAaAdLT2gIR0B9WV9Tgl4UdX2UKGgGR8BUwAAAAAAAaAdLVGgIR0B9WakgwGnodX2UKGgGR8BUQAAAAAAAaAdLUmgIR0B9WYTCcf/4dX2UKGgGR8BZgAAAAAAAaAdLZ2gIR0B9Wd94NZvDdX2UKGgGR8BUgAAAAAAAaAdLU2gIR0B9WeepXIU8dX2UKGgGR8BRQAAAAAAAaAdLRmgIR0B9WjhNucc3dX2UKGgGR8BbAAAAAAAAaAdLbWgIR0B9WlB/qgRLdX2UKGgGR8BbQAAAAAAAaAdLbmgIR0B9Wldu5z5odX2UKGgGR8BTgAAAAAAAaAdLT2gIR0B9WulQ/HHWdX2UKGgGR8BXQAAAAAAAaAdLXmgIR0B9Wyf/WDpUdX2UKGgGR8BVQAAAAAAAaAdLVmgIR0B9W/nB+F10dX2UKGgGR8BWQAAAAAAAaAdLWmgIR0B9W/IsAeaKdX2UKGgGR8BbgAAAAAAAaAdLb2gIR0B9W94wAU+LdX2UKGgGR8BTQAAAAAAAaAdLTmgIR0B9XOzOX3QEdX2UKGgGR8BTAAAAAAAAaAdLTWgIR0B9XTu5SWJKdX2UKGgGR8BXAAAAAAAAaAdLXWgIR0B9XVF8XvYwdX2UKGgGR8BWAAAAAAAAaAdLWWgIR0B9XTHR1HOKdX2UKGgGR8BSgAAAAAAAaAdLS2gIR0B9XUUrTYukdX2UKGgGR8BUQAAAAAAAaAdLUmgIR0B9Xbnied08dX2UKGgGR8BTAAAAAAAAaAdLTWgIR0B9XbsyBTXKdX2UKGgGR8BSAAAAAAAAaAdLSWgIR0B9XdN9H+ZPdX2UKGgGR8BTQAAAAAAAaAdLTmgIR0B9XjDdgv12dX2UKGgGR8BYgAAAAAAAaAdLY2gIR0B9Xsu6ErXldX2UKGgGR8BTAAAAAAAAaAdLTWgIR0B9XqqPwNLEdX2UKGgGR8BWwAAAAAAAaAdLXGgIR0B9Xue18b71dX2UKGgGR8BWwAAAAAAAaAdLXGgIR0B9X9r0rbxmdWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True]", "_shape": [6], "low": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]", "high": "[ 1.        1.        1.        1.       12.566371 28.274334]", "low_repr": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]", "high_repr": "[ 1.        1.        1.        1.       12.566371 28.274334]", "_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-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-Acrobot-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9ed36745a7a2a4fb5de35b3f1dcc6931f5a7623b38e1151d20022b1ba20f2b9
+size 143732

ppo-Acrobot-v1/_stable_baselines3_version

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

ppo-Acrobot-v1/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 0x7ddddfd2dc60>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ddddfd2dcf0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ddddfd2dd80>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ddddfd2de10>",
+        "_build": "<function ActorCriticPolicy._build at 0x7ddddfd2dea0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7ddddfd2df30>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ddddfd2dfc0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ddddfd2e050>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7ddddfd2e0e0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ddddfd2e170>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ddddfd2e200>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ddddfd2e290>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7ddddfec2440>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1708362910823365907,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_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": -0.015808000000000044,
+    "_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": 248,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True]",
+        "_shape": [
+            6
+        ],
+        "low": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]",
+        "high": "[ 1.        1.        1.        1.       12.566371 28.274334]",
+        "low_repr": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]",
+        "high_repr": "[ 1.        1.        1.        1.       12.566371 28.274334]",
+        "_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-Acrobot-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:505209d1551e214cd7877f770c35e4a04a87c6f89bdc413f595f3379f30f6132
+size 85802

ppo-Acrobot-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:489769350b45fe65ea8a912fc26015c6a71746041ef236c9395834c3a71e8285
+size 42482

ppo-Acrobot-v1/pytorch_variables.pth

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

ppo-Acrobot-v1/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.1.0+cu121
+- GPU Enabled: True
+- Numpy: 1.25.2
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": -83.0, "std_reward": 8.270429251254134, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-19T17:31:35.689133"}