Upload PPO LunarLander-v2 trained agent
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +1 -1
- ppo-LunarLander-v2/data +17 -17
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 229.02 +/- 28.04
|
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 0x7efded27dca0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7efded27dd30>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7efded27ddc0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7efded27de50>", "_build": "<function ActorCriticPolicy._build at 0x7efded27dee0>", "forward": "<function ActorCriticPolicy.forward at 0x7efded27df70>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7efded202040>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7efded2020d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7efded202160>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7efded2021f0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7efded202280>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7efded202310>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7efded27c2d0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1712322094998193614, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAGZhhbxSmOG5qtKvObuD9rVEWvy6okrPuAAAgD8AAIA/hsotPnRNhLxOz8Q5MYscuCr05r0ZhQO5AACAPwAAgD/QZqq+l+5KP100Fz7063C+OUeqvUVlvz0AAAAAAAAAAM19M72P3nm6N6OIuYmrg7TS30a7KqOfOAAAgD8AAIA/M5x1PcPtMrqqpjw8bU65NkPBHLvn3K01AACAPwAAgD8z+1S9rnWJuspfnTlSg5G20TNvutAHtrgAAIA/AACAP/O6tj2PxmG69FQzvLVnF7Z0HL+68quLNQAAgD8AAIA/WlGJPTiqwD0zLAC+RURVvvae5rv1oK69AAAAAAAAAAATqjA+D7BlP16BVbz6dZW+nTHVPbplYr0AAAAAAAAAANPvHT6sxpU/aneYPsmswL7Lsuw9pRPHOwAAAAAAAAAAAGwwPXsanrr6CJS7q9wEtWgUTbr0uao6AACAPwAAgD/m0YG93r2ZPcMDRz4zlGG+FGeFPZurKD0AAAAAAAAAAKYnsb0G+Sw/m3PjPXOhiL6xc586eHkkPQAAAAAAAAAAAPg0O7jm5rmJ3Q66VpmLtVFxmLpr1SY5AACAPwAAgD9aMaI9H031uaQaJrtm6++1mJCwOirDPjoAAIA/AACAP5rZ/ToU3sK6VjB1urXLTTuVXAs7MstevAAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_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:": "gAWVQQwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQE46o+fRNRGMAWyUS9iMAXSUR0B9G5wjt5UtdX2UKGgGR0BkWQu/UONHaAdN6ANoCEdAfSBwsGxD9nV9lChoBkdAZbcMUh3aBmgHTegDaAhHQH0qTfrKNhp1fZQoaAZHQGLwXjlxOtZoB03oA2gIR0B9MjCbc45tdX2UKGgGR0BgN8xIre67aAdN6ANoCEdAfUBIcinpCHV9lChoBkdAZnzzRQaaTmgHTegDaAhHQH1XYk/r0J51fZQoaAZHQGJF6F/QSjBoB03oA2gIR0B9Y6+Jxeb/dX2UKGgGR0Bk9//95yEMaAdN6ANoCEdAfW6lXzUZvXV9lChoBkdAZkiY+B6KL2gHTegDaAhHQH1wTUAksz51fZQoaAZHQGLLta6jFhpoB03oA2gIR0B9cY7cO9WZdX2UKGgGR0Bc9SUcGTs6aAdN6ANoCEdAfXRVxjriVHV9lChoBkdAYeGplSS/02gHTegDaAhHQH2EYpMHryF1fZQoaAZHQGPq/+sHSndoB03oA2gIR0B9iGaTfR/mdX2UKGgGR0AjM6QvHtF8aAdL9WgIR0B9jxEPUaybdX2UKGgGR0BkvO6d1+y7aAdN6ANoCEdAfY9VLBbfQHV9lChoBkdAY/ipo9LYgGgHTegDaAhHQH2bvc8DB/J1fZQoaAZHQGA3liSaEzxoB03oA2gIR0B9sKr+5vtMdX2UKGgGR0BVwfIOpbUxaAdN6ANoCEdAfbQI55qubXV9lChoBkdAY4/yEtdzGWgHTegDaAhHQH234+B6KLt1fZQoaAZHQGGtnWz4UN9oB03oA2gIR0B9v3di2DxtdX2UKGgGR0BlQdEuxrzoaAdN6ANoCEdAfcWYtQKrrHV9lChoBkdAZdEu5jH4oWgHTegDaAhHQH3Re4oZydZ1fZQoaAZHQGV/nw5NoJ1oB03oA2gIR0B95Do4dZJTdX2UKGgGR0BmLupMpPRBaAdN6ANoCEdAfe3TA31jAnV9lChoBkdAYjpjx0+1SmgHTegDaAhHQH32G47Rv3t1fZQoaAZHQGT8JXp4bCJoB03oA2gIR0B9+EKUmlZYdX2UKGgGR0BlShgiNbTuaAdN6ANoCEdAffpfyf+S83V9lChoBkdAXnHZAY51eWgHTegDaAhHQH4GqgyuZCx1fZQoaAZHQGUYNOEdvKloB03oA2gIR0B+CZntfG+9dX2UKGgGR0BkHnXoTwlTaAdN6ANoCEdAfg7QRPGhmHV9lChoBkdAYLzkWhysCGgHTegDaAhHQH4PBN21Ul11fZQoaAZHQGCpL1/Ue+5oB03oA2gIR0B+GXNY8uBddX2UKGgGR0BjccR6F/QTaAdN6ANoCEdAfhslvZRKpXV9lChoBkdAaOZFKkEcKmgHTegDaAhHQH43WVAzHjp1fZQoaAZHQGA+Wf9P1thoB03oA2gIR0B+Ot3fQ8fWdX2UKGgGR0Bc9qq814xDaAdN6ANoCEdAfkIHU+cH4XV9lChoBkdAYdlYEGJN02gHTegDaAhHQH5IDoUzsQd1fZQoaAZHQGRvT7l7tzFoB03oA2gIR0B+VBxAB1cMdX2UKGgGR0BlfCScLBsRaAdN6ANoCEdAfmhd/J/5L3V9lChoBkdAYp7/jKgZj2gHTegDaAhHQH5zC9EkSmJ1fZQoaAZHQF4l6jWTX8RoB03oA2gIR0B+fDffoA4odX2UKGgGR0BnANm6GxlhaAdN6ANoCEdAfn6qoZQ53nV9lChoBkdAYYtcHGCI12gHTegDaAhHQH6BLKFIuoR1fZQoaAZHQGTT1Ed/8VJoB03oA2gIR0B+kJ4mkWRBdX2UKGgGR0Bfgrns9jgAaAdN6ANoCEdAfpRhXr+o+HV9lChoBkdAXqEfyPMjeWgHTegDaAhHQH6bGEPDpC91fZQoaAZHQGJA7pV0cOtoB03oA2gIR0B+m1iqhlDndX2UKGgGR0Be0JTER8MNaAdN6ANoCEdAfqeyLQ5WBHV9lChoBkdAYUU6qbSZ0GgHTegDaAhHQH6pvQnhKlJ1fZQoaAZHQGC/l+3H7xdoB03oA2gIR0B+rVsLv1DjdX2UKGgGR0BkChrrPdEcaAdN6ANoCEdAfsZmmtQsPXV9lChoBkdAYNVarWAf+2gHTegDaAhHQH7PJTER8MN1fZQoaAZHQFwSiWVu76JoB03oA2gIR0B+1nHaN+9bdX2UKGgGR0Bj+lV/+bVjaAdN6ANoCEdAfuTP0qYqonV9lChoBkdAZQS32EkB0mgHTegDaAhHQH77OdXko4N1fZQoaAZHQGGgjA8B+4NoB03oA2gIR0B/Behf0EowdX2UKGgGR0Bk9RLCemNzaAdN6ANoCEdAfw82xY7q6nV9lChoBkdAZvOK+i8Fp2gHTegDaAhHQH8RjkMkQf91fZQoaAZHQGS2YNqgyuZoB03oA2gIR0B/E/IikftAdX2UKGgGR0BexIXoC+10aAdN6ANoCEdAfyE2M85jpnV9lChoBkdAZiXVhCtzS2gHTegDaAhHQH8kVhoduHh1fZQoaAZHQGNHrxRVIZtoB03oA2gIR0B/KdLxqfvndX2UKGgGR0BkG9fCyhSMaAdN6ANoCEdAfyoMUAT7EnV9lChoBkdAWxUXcgyM1mgHTegDaAhHQH8033UQTVV1fZQoaAZHQGClehGpdbBoB03oA2gIR0B/NrPw/gR9dX2UKGgGR0BldmQ6p5u7aAdN6ANoCEdAfzncy31BdHV9lChoBkdAZNCLiuMdcWgHTegDaAhHQH9Pj1XeWOZ1fZQoaAZHQGWurUkOZstoB03oA2gIR0B/V52eQMhHdX2UKGgGR0Be9L3sXzlLaAdN6ANoCEdAf16UxVQyh3V9lChoBkdAZC9ReC04R2gHTegDaAhHQH9so0IkZ751fZQoaAZHQF20+RYA80VoB03oA2gIR0B/hBcGC7K8dX2UKGgGR0BkzDj94u9OaAdN6ANoCEdAf5CpEhJRO3V9lChoBkdAXdVObiIcimgHTegDaAhHQH+blyaNMoN1fZQoaAZHQF9t6Skj5bhoB03oA2gIR0B/noKLKmsOdX2UKGgGR0BhIjWsijcmaAdN6ANoCEdAf6GFOfukUXV9lChoBkdAYu3b/wRXfmgHTegDaAhHQH+0UNKAavR1fZQoaAZHQGXf2fkFOfxoB03oA2gIR0B/uMytV7x/dX2UKGgGR0BgeByXD3ueaAdN6ANoCEdAf8CS1Vo6CHV9lChoBkdAYzSiO/+Kj2gHTegDaAhHQH/A5SWJJoV1fZQoaAZHQGUEO7QLNOdoB03oA2gIR0B/zyNMoMKDdX2UKGgGR0BnrDTBqKxcaAdN6ANoCEdAf9FugYgq3HV9lChoBkdAYDZs/IKc/mgHTegDaAhHQH/VdOVPepJ1fZQoaAZHQGJ6ml67dzpoB03oA2gIR0B/2hlz2exwdX2UKGgGR0BfMSgTRIBjaAdN6ANoCEdAf/b2HtWuHXV9lChoBkdAXokgzP8htGgHTegDaAhHQH/+K7mMfih1fZQoaAZHQGJaxf4REndoB03oA2gIR0CABdR64UeudX2UKGgGR0BCe1kUbkwOaAdL/WgIR0CADwwTM7lrdX2UKGgGR0BgjRbW3BpIaAdN6ANoCEdAgBAsaCL/CXV9lChoBkdAY4l1Oj7AL2gHTegDaAhHQIAVGkgwGnp1fZQoaAZHQGIHb0e2d/doB03oA2gIR0CAGWMb3oLYdX2UKGgGR0BkMsbtJFspaAdN6ANoCEdAgBp5ZB9kSXV9lChoBkdAYVjEit7rs2gHTegDaAhHQIAblyPuG9J1fZQoaAZHQGbA+VC5VfhoB03oA2gIR0CAIqmVJL/TdX2UKGgGR0BidUUKzAvdaAdN6ANoCEdAgCR1zySV4XV9lChoBkdAYGVTEzfrKWgHTegDaAhHQIAnoq/dqL11fZQoaAZHQGChQVsUIs1oB03oA2gIR0CAJ8NYr8R+dX2UKGgGR0BidtsJpnHvaAdN6ANoCEdAgC3PLHMlknV9lChoBkdAZEN9MsYl6mgHTegDaAhHQIAuzHlwLmZ1fZQoaAZHQGcpHLzPKMhoB03oA2gIR0CAMI9jgAIZdX2UKGgGR0Bg8IKrq+rVaAdN6ANoCEdAgDK9nbqQinVlLg=="}, "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 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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "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": 128, "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-6.2.0-39-generic-x86_64-with-glibc2.17 # 40~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Nov 16 10:53:04 UTC 2", "Python": "3.8.18", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.2+cu121", "GPU Enabled": "False", "Numpy": "1.24.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1"}}
|
|
|
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 0x7fb26a67dca0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb26a67dd30>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb26a67ddc0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb26a67de50>", "_build": "<function ActorCriticPolicy._build at 0x7fb26a67dee0>", "forward": "<function ActorCriticPolicy.forward at 0x7fb26a67df70>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fb26a602040>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb26a6020d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fb26a602160>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb26a6021f0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb26a602280>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb26a602310>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fb26a67c2a0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1712322867214142034, "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 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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "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": 256, "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:": "gAWV1gIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMYC9ob21lL2hvb2t6ZW5nL2FuYWNvbmRhMy9lbnZzL3B5MzgvbGliL3B5dGhvbjMuOC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4RDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMYC9ob21lL2hvb2t6ZW5nL2FuYWNvbmRhMy9lbnZzL3B5MzgvbGliL3B5dGhvbjMuOC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlGgAjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoH32UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHPzOpKjBVMmGFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="}, "system_info": {"OS": "Linux-6.2.0-39-generic-x86_64-with-glibc2.17 # 40~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Nov 16 10:53:04 UTC 2", "Python": "3.8.18", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.2+cu121", "GPU Enabled": "False", "Numpy": "1.24.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1"}}
|
ppo-LunarLander-v2.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 147601
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0b2c2670c646e9adb567ee37983c5a2347e6f9c0bd879a5c5c76caf2a92bd30
|
3 |
size 147601
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,20 +4,20 @@
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__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 ",
|
7 |
-
"__init__": "<function ActorCriticPolicy.__init__ at
|
8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
11 |
-
"_build": "<function ActorCriticPolicy._build at
|
12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
13 |
-
"extract_features": "<function ActorCriticPolicy.extract_features at
|
14 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
15 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
16 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
17 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
18 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
-
"_abc_impl": "<_abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
@@ -26,12 +26,12 @@
|
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
-
"start_time":
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
-
":serialized:": "
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -45,7 +45,7 @@
|
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
-
":serialized:": "
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
@@ -83,7 +83,7 @@
|
|
83 |
"ent_coef": 0.01,
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
-
"batch_size":
|
87 |
"n_epochs": 4,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__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 ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7fb26a67dca0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb26a67dd30>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb26a67ddc0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb26a67de50>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fb26a67dee0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fb26a67df70>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7fb26a602040>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb26a6020d0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fb26a602160>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb26a6021f0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb26a602280>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb26a602310>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7fb26a67c2a0>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1712322867214142034,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "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"
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "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"
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
|
|
83 |
"ent_coef": 0.01,
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 256,
|
87 |
"n_epochs": 4,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
ppo-LunarLander-v2/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 87978
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8dc3611144be90ec0b759e6a2e899010f1087dc869d805915d2e7687cb160554
|
3 |
size 87978
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43634
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cd470121d6a6803d49e8f98d556cb68fd0e952ec246b3763beb8964bce5454d
|
3 |
size 43634
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 229.01773050000003, "std_reward": 28.04352246627346, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-05T21:22:41.639231"}
|