SparkleDark commited on
Commit
2252c2d
1 Parent(s): 1038f60

Upload PPO LunarLander-v2 trained agent for RL course

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: LunarLander-v2
17
  metrics:
18
  - type: mean_reward
19
- value: 182.11 +/- 106.19
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: LunarLander-v2
17
  metrics:
18
  - type: mean_reward
19
+ value: 214.36 +/- 70.27
20
  name: mean_reward
21
  verified: false
22
  ---
config.json CHANGED
@@ -1 +1 @@
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 0x7e930076a9e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e930076aa70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e930076ab00>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e930076ab90>", "_build": "<function ActorCriticPolicy._build at 0x7e930076ac20>", "forward": "<function ActorCriticPolicy.forward at 0x7e930076acb0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e930076ad40>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e930076add0>", "_predict": "<function ActorCriticPolicy._predict at 0x7e930076ae60>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e930076aef0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e930076af80>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e930076b010>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e93007782c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1710949049083233886, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAOO2Tr5jvh8/07OZvZvoE78cJHu+0mr8PQAAAAAAAAAAzS1VPn9VdD87+Cw+SggFvzWUDz69cKk8AAAAAAAAAADN7Hg6nIq0PxH1xD2zOaC8JVaPun50srwAAAAAAAAAAPrXJL52EDe8DYxju0MnprmagZ49HWWWOgAAgD8AAIA/5go0Po8BErwOI505XWEyPK+gbL30txk9AACAPwAAgD9Aqom+VWIwP7DBOL6MUyS/BkmDvqj9fT0AAAAAAAAAAIDrAb4fgJY8uwgxPnSqAL549Rg8I/McPQAAAAAAAAAAAKC1Pt+/6j65goU8v3CNvh7E1T15m4M8AAAAAAAAAABakz0+dAegvNKPvLmg6Nc3lJ4RvuI0+DgAAIA/AACAP2C4Lr6K7Ic/c7/svmGmLL+iAWO+dhWKvQAAAAAAAAAADQEQvmzVi7uueVC7N2nUuN3B8zwU0II6AAAAAAAAgD/N86c9S8TQPR70ir0MfDO+93I0PG9kj70AAAAAAAAAAIDyAz2EAaU/JiRGPsNV9r7rcTM9usqMPQAAAAAAAAAAzV4YvnaCMbySTxc7K/EsOUatmT0BGEy6AACAPwAAgD8mnNS9w+lyunr+lDnD2EO4+8yXOmtVnbgAAIA/AAAAADOh1r1VRqQ/uMcJv+PMCr/5j7C9XQeBvgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAQAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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:": "gAWV/QsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHCxlpoK2KGMAWyUS+SMAXSUR0CXhXuOjqOcdX2UKGgGR0BxHN1r6+FlaAdL8GgIR0CXhfVQAMlUdX2UKGgGR0ByRgnmaH9FaAdLzWgIR0CXhjwrlNlAdX2UKGgGR0Bx3tOBUaQ4aAdNLwFoCEdAl4b8D8tPHnV9lChoBkdAb5Kosqaw2WgHS/BoCEdAl4cXKW9lE3V9lChoBkdAY0i9C/oJRmgHTegDaAhHQJeHY2WIGhV1fZQoaAZHQEods7+1jRVoB0vlaAhHQJeH38uSOip1fZQoaAZHQHDBO6Ae7tloB00HAWgIR0CXiRqS5iEydX2UKGgGR0Bxe//Pw/gSaAdLzWgIR0CXiSd2gWaddX2UKGgGR0Bxwy2QXAM2aAdL52gIR0CXiyJYT0xudX2UKGgGR0A3660Y0l7daAdLgWgIR0CXi/Er5IpZdX2UKGgGR0BxAsFjd56daAdNGwFoCEdAl4yiI+GGmHV9lChoBkdAcE0IczZYgmgHS9BoCEdAl4zTLOiWV3V9lChoBkdAYYZvuPV/c2gHTegDaAhHQJeM33WWhRJ1fZQoaAZHQHNIHXRPXTVoB0v0aAhHQJeNnj7yhBZ1fZQoaAZHQHJkQkcCHRFoB0vGaAhHQJeNmknCwbF1fZQoaAZHQHCI7ZBcAzZoB0vraAhHQJeOXw8W9Dh1fZQoaAZHQHA8SVjZteloB00tAWgIR0CXjtd7fHghdX2UKGgGR0ByS5Htnf2saAdNBgFoCEdAl48RxPwd83V9lChoBkdAcZ/eKKpDNWgHS+VoCEdAl5AgJswcpHV9lChoBkdAcXfz0HyEtmgHS+NoCEdAl5Aco2GZeHV9lChoBkdAcMZJAMUh3mgHS8poCEdAl5FAG8mKInV9lChoBkdATIRv73wkPmgHS7doCEdAl5Ir5RCQcXV9lChoBkdAb79enAIppmgHS/xoCEdAl5OZfdAPd3V9lChoBkdAZPUuJ1q33GgHTegDaAhHQJeTmFFlTWJ1fZQoaAZHQHEibwjMV1xoB0vtaAhHQJeTuQKa5PN1fZQoaAZHQHD6B0lqrR1oB0v+aAhHQJeVTGQ0XP91fZQoaAZHQGyzW7voePtoB0vzaAhHQJeV047zTWp1fZQoaAZHQHAtpH/cWTJoB0vmaAhHQJeV7E5yU9p1fZQoaAZHQHFOsunMt9RoB0v+aAhHQJeW7Uoa1kV1fZQoaAZHQEQN779AHFBoB0vwaAhHQJeXrG7z06J1fZQoaAZHQHKk9Q0oBq9oB0v5aAhHQJeX+x8lXzV1fZQoaAZHQHCI14oqkM1oB01zAWgIR0CXmDlk6LfldX2UKGgGR0Bl6x1klNUPaAdN6ANoCEdAl5kmfkFOf3V9lChoBkdAcsu2CuloDmgHS+1oCEdAl5mxsl9jPXV9lChoBkdAcp/wQlKK52gHTQ0BaAhHQJeZxGMGX5Z1fZQoaAZHQG5bg75mAb1oB0vTaAhHQJeaWbiIcip1fZQoaAZHQG3vL/0dzXBoB0vhaAhHQJeaoNDtw711fZQoaAZHQGIi9+XqqwRoB03oA2gIR0CXmsR3u/lAdX2UKGgGR0Bwj/Mr3CbdaAdNCAFoCEdAl5up/LDAJ3V9lChoBkdAb04mY0EX+GgHS+poCEdAl5xScCo0h3V9lChoBkdAcNQIToMa0mgHS+BoCEdAl5yDZ13dK3V9lChoBkdAcVfOWSlnAmgHS+doCEdAl57DYRNAT3V9lChoBkdAcBaD9wWFe2gHTSkBaAhHQJee0Gnn+yZ1fZQoaAZHQG8CJeeFtbdoB0vjaAhHQJee446wMYx1fZQoaAZHQGA47dBSk0toB03oA2gIR0CXnvW0Z3s5dX2UKGgGR0Bv5Mlsxfv4aAdNJQFoCEdAl5+S6pYLcHV9lChoBkdAbkC1kUbkwWgHS/RoCEdAl6Afnr6ciHV9lChoBkdAbp9pQk5ZKWgHS+NoCEdAl6A3rleWwHV9lChoBkdAcmSxm03OwGgHTTABaAhHQJegcuwosqd1fZQoaAZHQHA3YPsiSq5oB00IAWgIR0CXoSKqn3tbdX2UKGgGR0BwBy4Wk8A8aAdL+mgIR0CXoVgsK9f1dX2UKGgGR0BwnwWYWtU5aAdL+mgIR0CXoZfHxSYPdX2UKGgGR0BwgZyGSIP9aAdNBAFoCEdAl6H1psXSB3V9lChoBkdAO9e98JD3NGgHS9BoCEdAl6IXryDqW3V9lChoBkdAbw1SqlxffGgHS/toCEdAl6KF18stkHV9lChoBkdAciRduYQarGgHS/toCEdAl6M1HnU2DXV9lChoBkdAb0FaUzKs+2gHS9doCEdAl6Q24d6syXV9lChoBkdAb/YFTNt65WgHS8loCEdAl6SXgLqlg3V9lChoBkdAbqhMFlkH2WgHS/toCEdAl6UtBv73wnV9lChoBkdAccVHuqm0mmgHTQQBaAhHQJel0eHSF491fZQoaAZHQG+4oRZlnRNoB0vFaAhHQJem4fhddE91fZQoaAZHQHBFahQFcIJoB0vzaAhHQJenA7yQPqd1fZQoaAZHQG5KYu01IiFoB00EAWgIR0CXp41HOKO1dX2UKGgGR0Bs8Mo6S1VpaAdL32gIR0CXp5do371qdX2UKGgGR0BwzZcC5mROaAdL/mgIR0CXp8xJd0JXdX2UKGgGR0BwWYGJN0vHaAdL2GgIR0CXp/eumrKedX2UKGgGR0BxPjlS0jTsaAdNVAFoCEdAl6imqxTsIHV9lChoBkdAcZ7qUeMho2gHS99oCEdAl6isir1dxHV9lChoBkdAYRQuJUHY6GgHTegDaAhHQJesA2sJY1Z1fZQoaAZHQHFXGGyon8doB00oAWgIR0CXrZ2oegctdX2UKGgGR0Bw4c5jpcHGaAdL/2gIR0CXrgJlar3kdX2UKGgGR0Bwn+SRr8BNaAdNFQFoCEdAl65Durp7kXV9lChoBkdAcaXyaNMoMWgHS/hoCEdAl65s+/xlQXV9lChoBkdAcaFcf/3nIWgHS8toCEdAl68LzwtrbnV9lChoBkdAQCiubI91U2gHS8poCEdAl68rrcCYC3V9lChoBkdAcWfCK77KrGgHS+ZoCEdAl6892gWadHV9lChoBkdAckd7nxJ/X2gHTREBaAhHQJevlEYwZfl1fZQoaAZHQHGuuZXuE25oB0v0aAhHQJev97PY4AF1fZQoaAZHQG8ED2i+L3toB0vfaAhHQJewTaDf3vh1fZQoaAZHQG9Zadc0LtxoB0vraAhHQJewoVFhG6R1fZQoaAZHQHASsHjZL7JoB0vGaAhHQJezPC66J691fZQoaAZHQHGtHZ9NN8FoB0v7aAhHQJezn2ys0YV1fZQoaAZHQECt+Haews5oB0vLaAhHQJe0C9lEqlR1fZQoaAZHQHGwOokzGgloB0vZaAhHQJe0reGfwql1fZQoaAZHQHEMU6o2n89oB0vHaAhHQJe0zAmAskJ1fZQoaAZHQG3rOp84PwxoB0vsaAhHQJe2J5LRKHx1fZQoaAZHQBWKmj0th/loB0vSaAhHQJe2NRDTjNp1fZQoaAZHQHAykgntv4xoB0vQaAhHQJe2hZNfw7V1fZQoaAZHQHFkv3vhIe5oB0v/aAhHQJe2pz5oGpx1fZQoaAZHQG5n4QSSNfhoB0vzaAhHQJe3642CNCJ1fZQoaAZHQHIkjKHO8kFoB01RAWgIR0CXt+w/PgNxdX2UKGgGR0BxnzQAuIykaAdNUQFoCEdAl7mNoJzDGnV9lChoBkdAcRdPLPldT2gHS/xoCEdAl7sklzEJjXV9lChoBkdAcB4l6JIlMWgHS9BoCEdAl7sxGMGX5XV9lChoBkdAcQ8s0HhS+GgHS/hoCEdAl7tugL7XQXV9lChoBkdAbSVDgIhQnGgHTQQBaAhHQJe8QeOn2qV1fZQoaAZHQHDKwV0tAcFoB0vQaAhHQJe8yJm/WUd1fZQoaAZHQD70/QjUuthoB0vCaAhHQJe80cyWRih1fZQoaAZHQHFEOQEIPbxoB0vXaAhHQJe9WEIw/Ph1ZS4="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 310, "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-6.1.58+-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": "2.2.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
 
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 0x7e930076a9e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e930076aa70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e930076ab00>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e930076ab90>", "_build": "<function ActorCriticPolicy._build at 0x7e930076ac20>", "forward": "<function ActorCriticPolicy.forward at 0x7e930076acb0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e930076ad40>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e930076add0>", "_predict": "<function ActorCriticPolicy._predict at 0x7e930076ae60>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e930076aef0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e930076af80>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e930076b010>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e93007782c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1710949049083233886, "learning_rate": 0.0, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAQAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": 310, "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, "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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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": "2.2.1+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 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f7509fe5f0f1eabf1d52710055b5c8e7cb20f2aee201831c63e6763ac4a2ef3
3
- size 147991
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2787c9e77ceaf847ad78fcd7ab4e9308a734031c7068733e0272ef637737c34
3
+ size 147820
ppo-LunarLander-v2/data CHANGED
@@ -27,7 +27,7 @@
27
  "seed": null,
28
  "action_noise": null,
29
  "start_time": 1710949049083233886,
30
- "learning_rate": 0.0003,
31
  "tensorboard_log": null,
32
  "_last_obs": {
33
  ":type:": "<class 'numpy.ndarray'>",
@@ -52,6 +52,21 @@
52
  ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
53
  },
54
  "_n_updates": 310,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  "observation_space": {
56
  ":type:": "<class 'gymnasium.spaces.box.Box'>",
57
  ":serialized:": "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",
@@ -69,7 +84,7 @@
69
  },
70
  "action_space": {
71
  ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
72
- ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
73
  "n": "4",
74
  "start": "0",
75
  "_shape": [],
@@ -77,23 +92,8 @@
77
  "_np_random": null
78
  },
79
  "n_envs": 16,
80
- "n_steps": 2048,
81
- "gamma": 0.99,
82
- "gae_lambda": 0.95,
83
- "ent_coef": 0.0,
84
- "vf_coef": 0.5,
85
- "max_grad_norm": 0.5,
86
- "batch_size": 64,
87
- "n_epochs": 10,
88
- "clip_range": {
89
- ":type:": "<class 'function'>",
90
- ":serialized:": "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"
91
- },
92
- "clip_range_vf": null,
93
- "normalize_advantage": true,
94
- "target_kl": null,
95
  "lr_schedule": {
96
  ":type:": "<class 'function'>",
97
- ":serialized:": "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"
98
  }
99
  }
 
27
  "seed": null,
28
  "action_noise": null,
29
  "start_time": 1710949049083233886,
30
+ "learning_rate": 0.0,
31
  "tensorboard_log": null,
32
  "_last_obs": {
33
  ":type:": "<class 'numpy.ndarray'>",
 
52
  ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
53
  },
54
  "_n_updates": 310,
55
+ "n_steps": 2048,
56
+ "gamma": 0.99,
57
+ "gae_lambda": 0.95,
58
+ "ent_coef": 0.0,
59
+ "vf_coef": 0.5,
60
+ "max_grad_norm": 0.5,
61
+ "batch_size": 64,
62
+ "n_epochs": 10,
63
+ "clip_range": {
64
+ ":type:": "<class 'function'>",
65
+ ":serialized:": "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"
66
+ },
67
+ "clip_range_vf": null,
68
+ "normalize_advantage": true,
69
+ "target_kl": null,
70
  "observation_space": {
71
  ":type:": "<class 'gymnasium.spaces.box.Box'>",
72
  ":serialized:": "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",
 
84
  },
85
  "action_space": {
86
  ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
87
+ ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
88
  "n": "4",
89
  "start": "0",
90
  "_shape": [],
 
92
  "_np_random": null
93
  },
94
  "n_envs": 16,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
95
  "lr_schedule": {
96
  ":type:": "<class 'function'>",
97
+ ":serialized:": "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"
98
  }
99
  }
ppo-LunarLander-v2/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:afe5f37884cb02a76e6d333a25fd7a7eee75d739eca1a82890ed75ec5e9ac02e
3
- size 88362
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a3cb2360c0a2546be9ae0915134ff5bd4835a846b46b647d11b1056d0bd508f
3
+ size 88490
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 182.10588631269357, "std_reward": 106.19175067697715, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-20T16:07:48.808328"}
 
1
+ {"mean_reward": 214.35975119999998, "std_reward": 70.27435921602986, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-20T16:13:42.991063"}