Trying RL: PPO for the First Time

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- LunarLander-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: 271.17 +/- 14.58
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **LunarLander-v2**
+This is a trained model of a **PPO** agent playing **LunarLander-v2**
+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 0x7c3a565f6c20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c3a565f6cb0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c3a565f6d40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c3a565f6dd0>", "_build": "<function ActorCriticPolicy._build at 0x7c3a565f6e60>", "forward": "<function ActorCriticPolicy.forward at 0x7c3a565f6ef0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c3a565f6f80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c3a565f7010>", "_predict": "<function ActorCriticPolicy._predict at 0x7c3a565f70a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c3a565f7130>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c3a565f71c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c3a565f7250>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c3a565a17c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000.0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1717340057620545257, "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": 397, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "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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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2c4f6bc3cc428a2a2a6aa5d88e3b847406a306fa58e31b01056cbc9fd3c20a4
+size 147961

ppo-LunarLander-v2/_stable_baselines3_version

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

ppo-LunarLander-v2/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 0x7c3a565f6c20>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c3a565f6cb0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c3a565f6d40>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c3a565f6dd0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7c3a565f6e60>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7c3a565f6ef0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c3a565f6f80>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c3a565f7010>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7c3a565f70a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c3a565f7130>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c3a565f71c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c3a565f7250>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7c3a565a17c0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000.0,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1717340057620545257,
+    "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:": "gAWV5AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHJ6pEc81XOMAWyUS+eMAXSUR0CnKmIuGsV+dX2UKGgGR0BzEa/+KjzqaAdL4GgIR0CnK5cm0E5idX2UKGgGR0BxdIW69TP0aAdL1GgIR0CnK6oGyHEddX2UKGgGR0Bw09VBD5TIaAdLw2gIR0CnK7Sde6ZqdX2UKGgGR0BwWapEQXhwaAdLw2gIR0CnK7dsi0OWdX2UKGgGR0Bw0fYpUgjhaAdLy2gIR0CnK7kmplz2dX2UKGgGR0BwSQ9lmOENaAdLtmgIR0CnLCHN5dGBdX2UKGgGR0By3DIOpbUxaAdL9mgIR0CnLCVzIV/MdX2UKGgGR0Bwf/A+IMz/aAdLwGgIR0CnLD66STyKdX2UKGgGR0Bw21QAMlTnaAdLt2gIR0CnLD8IZ62OdX2UKGgGR0BvarN8ma6SaAdL0mgIR0CnLFL8BMi9dX2UKGgGR0ByY8zch1TzaAdL82gIR0CnLF9jPOY6dX2UKGgGR0ByZL5GjKxLaAdLuWgIR0CnLIaBy0a7dX2UKGgGR0ByXnppvgm7aAdLxmgIR0CnLI7ItDlYdX2UKGgGR0BycTeWOZLJaAdL9WgIR0CnLPqcEvCedX2UKGgGR0BwX6EpRXOoaAdLumgIR0CnLcUdilSCdX2UKGgGR0BxUl5xBE8aaAdLuGgIR0CnLdI/Z/TcdX2UKGgGR0BwHxMURFqjaAdLxGgIR0CnLguOS4e+dX2UKGgGR0BwmJE0BOpLaAdLyWgIR0CnLhnzxwyZdX2UKGgGR0BxX8KArhBJaAdL4WgIR0CnLmoU8FINdX2UKGgGR0BvLB1q33HraAdLvmgIR0CnLm/wy6+WdX2UKGgGR0Bx4BkWhysCaAdLxmgIR0CnLqre67NCdX2UKGgGR0BxlZ0EHMUzaAdLz2gIR0CnLsjv/io9dX2UKGgGR0Bm30MPSUkfaAdN6ANoCEdApy7mTq0MPXV9lChoBkdAcsVar3j+72gHS89oCEdApy7jdBSk03V9lChoBkdAcWLMmWt2cWgHS9poCEdApy8PEXLvC3V9lChoBkdAc1qOOKfnOmgHS/JoCEdApy8eQEIPb3V9lChoBkdAccm+0w8GLWgHS9BoCEdApy8i77Kq43V9lChoBkdAcT8LmZE2HmgHS+doCEdApy9Xd/J/5XV9lChoBkdAcY7WT5ftyGgHS9JoCEdApy+KOBDohnV9lChoBkdAcOkUjLSuyWgHS9ZoCEdApzBq8QI2O3V9lChoBkdAcHatWMju8mgHS7BoCEdApzB/Qa72+XV9lChoBkdAcYhg2Ifr8mgHS+FoCEdApzCCYqoZRHV9lChoBkdAbrl7IDHOr2gHS8JoCEdApzD8WsRxtHV9lChoBkdAcmc+evpyImgHS/FoCEdApzENXtBv73V9lChoBkdAc6ksUqQRw2gHS/RoCEdApzEJib2DhHV9lChoBkdAcpP6DXe3yGgHS+RoCEdApzExwhnrZHV9lChoBkdAcuJ4k/r0KGgHS8doCEdApzE/+fh/AnV9lChoBkdAcMiFNcnmaGgHS89oCEdApzFTMibDuXV9lChoBkdAcu4ySFGoaWgHS9hoCEdApzFbM1TBInV9lChoBkdAc3i/qxC6YmgHS9FoCEdApzGCrDIiknV9lChoBkdAcvERpDeCTWgHS9NoCEdApzGWjsUqQXV9lChoBkdAcBjGvfTCtWgHS9FoCEdApzGWA08/2XV9lChoBkdAcQNK1G9YfWgHS8toCEdApzHr7ALy+nV9lChoBkdAbvBQKrq+rWgHS65oCEdApzKGVC5VfnV9lChoBkdAck4Kb8WKuWgHS8xoCEdApzLQlByCF3V9lChoBkdAcW2pVjqfOGgHS9NoCEdApzL/vQWvbHV9lChoBkdAcd16gdwNsmgHS7NoCEdApzMgF1SwW3V9lChoBkdAbzYiBXjlxWgHS8doCEdApzNcoDxLCnV9lChoBkdAcPnj8DSw4mgHS7JoCEdApzNnRArxzHV9lChoBkdAcIYLNfPX1GgHS8RoCEdApzN+OQyRCHV9lChoBkdAcvKRTjvNNmgHS9RoCEdApzN7hNucc3V9lChoBkdAcXusFdLQHGgHS9toCEdApzPS8Hv+fnV9lChoBkdAcSULhaTwD2gHS9ZoCEdApzPiZ0CA+nV9lChoBkdAcepQ9ic5KmgHS89oCEdApzQR8MNMG3V9lChoBkdAZOl0NjLB9GgHTegDaAhHQKc0H4VRDTl1fZQoaAZHQHIuJpJwsGxoB0vnaAhHQKc0Pw7T2Fp1fZQoaAZHQHJdmyPdVNpoB0vwaAhHQKc0acf/3nJ1fZQoaAZHQG0+MTnJT2poB0uwaAhHQKc0oG/N7jV1fZQoaAZHQHEtz9KmKqJoB0vDaAhHQKc1G2rGR3h1fZQoaAZHQEpDqJMxoIxoB0ujaAhHQKc1V7KJVKh1fZQoaAZHQHGInKbKA8VoB0vRaAhHQKc1bB42S+x1fZQoaAZHQHGXEVvddmhoB0vHaAhHQKc1bEuQIUt1fZQoaAZHQHQC+yRjjJdoB0u/aAhHQKc1idmxt551fZQoaAZHQHEUPZRKpUBoB0vGaAhHQKc1tYukDZF1fZQoaAZHQHIiay8jAzpoB0voaAhHQKc2BK2a2F51fZQoaAZHQG9CedbxEv1oB0vPaAhHQKc2ILa24NJ1fZQoaAZHQG2zZC4SYgJoB0vCaAhHQKc2Qhq0tyx1fZQoaAZHQHDB+dwvQF9oB0u1aAhHQKc2P3dKujh1fZQoaAZHQHHa2ilBQepoB0v1aAhHQKc2nWcSXdF1fZQoaAZHQHLPG9g4OtpoB0vraAhHQKc2rIRRMvh1fZQoaAZHQHFK7/sE7nxoB0vOaAhHQKc288yN4qx1fZQoaAZHQHA3F58jRlZoB0vAaAhHQKc3hq0MPSV1fZQoaAZHQHJhg/X5FgFoB0vPaAhHQKc33Dbah6B1fZQoaAZHQG81dV3ljmVoB0vSaAhHQKc4CkHD7651fZQoaAZHQG7Kwb+98JFoB0voaAhHQKc4MLw4KhN1fZQoaAZHQG/X7iQ1aW5oB0vCaAhHQKc4aWSEDhd1fZQoaAZHQG6vlK02LpBoB0u9aAhHQKc4m4nWrfd1fZQoaAZHQHNKwZCOWB1oB0vjaAhHQKc4/7qIJqt1fZQoaAZHQHGiTBEa2ndoB00OAWgIR0CnORoJAt4BdX2UKGgGR0Bwi2yC4BmxaAdLxGgIR0CnOS62nbZfdX2UKGgGR0BxcaT7l7tzaAdL2WgIR0CnOYokJKJ3dX2UKGgGR0BxVrwpe/pMaAdL32gIR0CnOfz1kDp1dX2UKGgGR0BwcjMbFS88aAdLp2gIR0CnOms9KVY7dX2UKGgGR0BwpsDifg76aAdL3GgIR0CnOqe9SMtLdX2UKGgGR0BwOLaWX1J2aAdL1GgIR0CnOt0EovzwdX2UKGgGR0ByGIRkEs8QaAdLu2gIR0CnOyCdjG1hdX2UKGgGR0Bx2XcJtzjnaAdLz2gIR0CnOy1DSgGsdX2UKGgGR0BwgIPczqKQaAdLtGgIR0CnO66IWP92dX2UKGgGR0BoJ4H5aePJaAdN6ANoCEdApzvgbADaG3V9lChoBkdAcNwQ9zOopGgHS+VoCEdApzwb61stTXV9lChoBkdAcE8z7di2D2gHS8RoCEdApzwjFMqSYHV9lChoBkdAb3xmlqJuVGgHS9RoCEdApzyDe2uxKXV9lChoBkdAcDOD9wWFe2gHS9ZoCEdApz2hEH+qBHV9lChoBkdAcRrVR1oxpWgHS7NoCEdApz3Ms+V1OnV9lChoBkdAc1r8lXzUZ2gHS/5oCEdApz3Ko/A0sXV9lChoBkdAcrPDaXa8H2gHS+JoCEdApz5kEq2BrnV9lChoBkdAcGzqcmShamgHS8poCEdApz6HbM5fdHV9lChoBkdAcfI6tT1kD2gHS75oCEdApz6icNH6M3V9lChoBkdAcTTA9mpVCGgHS8toCEdApz7vxYq5LHVlLg=="
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 397,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True  True  True]",
+        "_shape": [
+            8
+        ],
+        "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]",
+        "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]",
+        "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]",
+        "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
+        "n": "4",
+        "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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"
+    }
+}

ppo-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:648b4d07ad992dd33121d66f820ea45da1caf92e5df2b41fc543b9fc68b2dfb7
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f69cfea67a312ca7fd14f9e16db99a6fc46827dd8a2c594fec68d9a95a7f2d4c
+size 43762

ppo-LunarLander-v2/pytorch_variables.pth

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

ppo-LunarLander-v2/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.3.0+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": 271.17151540000003, "std_reward": 14.576817523075354, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-02T15:37:31.879975"}