Upload PPO LunarLander-v2 trained agent
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +21 -21
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- ppo-LunarLander-v2/system_info.txt +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: 228.82 +/- 62.62
|
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 0x7db8705c32e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7db8705c3370>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7db8705c3400>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7db8705c3490>", "_build": "<function ActorCriticPolicy._build at 0x7db8705c3520>", "forward": "<function ActorCriticPolicy.forward at 0x7db8705c35b0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7db8705c3640>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7db8705c36d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7db8705c3760>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7db8705c37f0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7db8705c3880>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7db8705c3910>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7db87075f300>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1024000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1717364076371537963, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVtQYAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZABgAAAAAAANpgMr5SkJW7ktOJO0NQyTiGNeQ8SimgugAAgD8AAIA/ACyvu2e+uj9+pdK9CSmUPp6Alzvm9Yk9AAAAAAAAAAAzI586e9KjuqUgfzm8ZpY2GxmdOorLk7gAAIA/AACAP9r3gb0mLrQ/uoUzvhK1eL55kIS9noOevQAAAAAAAAAAzSwGulz3JrqW3o47/8UZN3+nMzsMtBM2AACAPwAAgD+zad49riOfuk5VfruEzFs4gLcAu8o3DjgAAIA/AACAP02hMT7s9eI61rWmOVtnLjXR/m48ajLBuAAAgD8AAIA/OlInvim8cTnCWTe7ipAtvEwGo7t+YRg9AACAPwAAAADzYbW9e7KBuhIM7zpimB+2utmQu5ueCboAAAAAAACAP6aZqL3DQVG69JqUO5E4tzY2O7I60FavugAAgD8AAIA/M9CiPK6lgLpoa8A8EQyAvI7xF7xzR2C9AACAPwAAgD9ware+f5baPvU8RDxuBL++Pm82PUqYHD0AAAAAAAAAAJpe8L2hocA9nQR0PeL6g74ToJE8DAOAOwAAAAAAAAAAhrJivq5ciDsCV2m8MRyOOW2hDr1F/3+6AACAPwAAgD9zfE0+lvIwP4iOeb4xbVu+2YG6vJ3lB74AAAAAAAAAAJqSRj7hBuU7WhWtOovHtbcHw409nKgiOQAAgD8AAIA/AGR6PI/mFLpNuES7HmVHNkzhxTvOkiw6AACAPwAAgD/M4ji/Ul4Bvqygmzjuvis3JuJIPlx9DLgAAIA/AACAP81b8rzd1rI/1q+TvbO6Qr4/ati9bjo0vgAAAAAAAAAAM008vv4ymj+Gy9m+qrmVvpLGR75ezWO9AAAAAAAAAADmrMS9hfPYud4yyjq6GmE2h5tRO9iY7rkAAIA/AACAP9O4J742ciq8QH4CvPF8yDniTY494tDoOgAAgD8AAIA/AGhqPGYseD+urCS95tSsvsaB67wi6cW9AAAAAAAAAAAAKhq8XCtQut4+Fjx9/Am5JyCDuQ8dALgAAIA/AACAP5oxibsdtK0/tsf9Oj4Kgr5uOJe8m8AuvQAAAAAAAAAAM8javCmIiD+x6pE8boaOvso4U7oonVE9AAAAAAAAAAAgjhC+v7m8PpZKIL2Mtqm+x+FIPYhl1LwAAAAAAAAAAGb8BzyPchC61TX1uSkgz7WAl+Q6kY0NOQAAgD8AAIA/BrqfPsCZjz9kjaw+f3MivrFQUD6l9nc9AAAAAAAAAADNz8i8FPaAuuB127hmKxMztER7u6Bl+zcAAIA/AACAP20fOT4u0Yc9Kj5EvBGqkb46hdQ88N3+PQAAAAAAAAAAzYlHveyImT/wfVC+kprCviNQhzxgEUC9AAAAAAAAAACAwi0+uL6fu4tUY7vtqdk4ltIEvRZ5LDoAAIA/AACAP0M4pj6uaZ682jEIOoHgC7ic/NW9kvAfuQAAgD8AAIA/poWBvbg+mLlU04+5jQ8rtF1mEDuh3qc4AACAPwAAgD+T7kS+PRQBuyUqiLvjivu3jpHoO0I9nzoAAIA/AACAP5rA4r3q0I8/hvBIvvbEeb4J2Q2+uuiRvAAAAAAAAAAATQl1PSlwbbp21Ne8buWoPAktlzriMpI9AAAAAAAAAADN6k48e/Scupr58Lya6C29QcpzO/CClT0AAAAAAAAAAGZyR73hdIi62g+LO/lf6zY4Eoc6vgedugAAgD8AAIA/JZ3FvsoADr2OvSe7jHM3uVMM0D2uO0A6AACAPwAAgD+T6XM+ysKbP04puT6FP4S+gt1WPjI0LjoAAAAAAAAAADrIcb6UuhW9vp3svLzIgrv5sYM+qqdBPAAAgD8AAIA/jea5vSmgIrqAqOs8vO6JNEJsGDqiOgkzAACAPwAAAABDVpm+w+FKupCHELoj+1Q256asOog1JDkAAIA/AACAPwBEFL578si68PNgO8DnDDjPuzQ80xyDugAAgD8AAIA/mgvEvpIIhzzWJaG78Z8iPL+sOj1nMzk7AACAPwAAgD+aon29j6IZuhdUQzmguVg0WMb/OpgdYLgAAIA/AACAP80SOj02NFm8In7evaDkKjxySsa9gGIQPQAAgD8AAIA/mm0uPtfxRD+RiC8+r+2bvq+RGTxeopq8AAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSzJLCIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVpQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYyAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksyhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.02400000000000002, "_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": 88, "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": 50, "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-6.1.85+-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"}}
|
|
|
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 0x7b9448194940>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b94481949d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b9448194a60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b9448194af0>", "_build": "<function ActorCriticPolicy._build at 0x7b9448194b80>", "forward": "<function ActorCriticPolicy.forward at 0x7b9448194c10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b9448194ca0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b9448194d30>", "_predict": "<function ActorCriticPolicy._predict at 0x7b9448194dc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b9448194e50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b9448194ee0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b9448194f70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b9448123180>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1720997113961289202, "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:": "gAWVMwwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQGGHWvB7/n6MAWyUTegDjAF0lEdAk+/3SSeRP3V9lChoBkdAYqM95hScb2gHTegDaAhHQJPx0pz90ih1fZQoaAZHQG98I6bONYNoB01bAmgIR0CT9Gw2l2vCdX2UKGgGR0BgJ2grYoRaaAdN6ANoCEdAk/jSGi5/b3V9lChoBkdAZ0ar/82rGWgHTegDaAhHQJP+0uJ1q351fZQoaAZHQGGB3vhIe5poB03oA2gIR0CT/xliSaE0dX2UKGgGR0BoGlCswL3LaAdN6ANoCEdAlABROLzf8HV9lChoBkdAZof7fpD/l2gHTegDaAhHQJQVv/JeVs11fZQoaAZHQHGWCtA9mpVoB02AAWgIR0CUGU9lmOENdX2UKGgGR0BmLCJ66asqaAdN6ANoCEdAlBr0TcqOLnV9lChoBkdAYSqsIVuaW2gHTegDaAhHQJQbEZEUj9p1fZQoaAZHQHDOiwnpjc5oB031AWgIR0CUG5QVbiZOdX2UKGgGR0Bx2iXsw+MZaAdNDgNoCEdAlBxNZJTVD3V9lChoBkdAcXOMKkVN6GgHTVUDaAhHQJQhMafjCHh1fZQoaAZHQHGNO1fE4vNoB01jA2gIR0CUIUuh9LHudX2UKGgGR0Bn9UXBP9DQaAdN6ANoCEdAlCOgi7kGRnV9lChoBkdAYjqSNfgJkWgHTegDaAhHQJQnTLaEi+t1fZQoaAZHQGt9wXZXdTJoB02oAmgIR0CULgoNNJvpdX2UKGgGR0BHSl7dBSk1aAdNAAFoCEdAlDQWvKU3XXV9lChoBkdAZDo8NhE0BWgHTegDaAhHQJQ0I2606YF1fZQoaAZHQG5f9vCMxXZoB021AWgIR0CUNR6kIomYdX2UKGgGR0By93rKNhmYaAdNnQJoCEdAlDYcPz4DcXV9lChoBkdAbBxkGRmseWgHTdYBaAhHQJQ2Rmf5DZ11fZQoaAZHQHB5AGW2PT5oB01bAWgIR0CUNuYrrgO0dX2UKGgGR0ByQirzXjEOaAdNkAFoCEdAlDmI7Rv3rXV9lChoBkdAaGD+d9Ujs2gHTegDaAhHQJQ5rBbfP5Z1fZQoaAZHQHD52uDBdldoB02rAmgIR0CUPs4c3l0YdX2UKGgGR0BMolqzqrzYaAdL3WgIR0CUQAIre67NdX2UKGgGR0Bws9IoVmBfaAdNhgNoCEdAlEBAv+OwPnV9lChoBkdAUNHdgv114mgHS+doCEdAlEFkV8CxNnV9lChoBkdAbdpHdXT3I2gHTbQDaAhHQJRCFJHy3Ct1fZQoaAZHQG1pKziS7oVoB01YA2gIR0CUQ1A4XGfgdX2UKGgGR0AkEALiMo+faAdLrmgIR0CUXWOpKjBVdX2UKGgGR0BBYlTFVDKHaAdL72gIR0CUXsK+zt1IdX2UKGgGR0BxlHRtxdY5aAdNTwJoCEdAlF+KmTC+DnV9lChoBkdAbm8H6/IsAmgHTbECaAhHQJRfnqcEvCd1fZQoaAZHQE+FuEVWS2ZoB0vdaAhHQJRh5Bw++uh1fZQoaAZHQHBPKpLmITJoB032AWgIR0CUYssQd0aIdX2UKGgGR0Bk2NHz6JqJaAdN6ANoCEdAlGNmVE/jbXV9lChoBkdAbLV4Oc2BKGgHTUUCaAhHQJRkCaCtihF1fZQoaAZHQGjDnpB5X2doB03oA2gIR0CUZKe/Ho5hdX2UKGgGR0BvpybYsd1daAdNTQJoCEdAlGh/BSDRMXV9lChoBkdAcXSqMm4RVmgHTdMBaAhHQJRqNSS/0ul1fZQoaAZHQEKUXAM2FWZoB0utaAhHQJRqTrNW2gF1fZQoaAZHQG9/sSCe2/loB039AWgIR0CUat9i+cpcdX2UKGgGR0BvttOGj9GaaAdNOQFoCEdAlGup/9YOlXV9lChoBkdAO8d0ihWYGGgHS+BoCEdAlGvrqdH2AXV9lChoBkdAcd2fv4M4LmgHTTYDaAhHQJRvY8W9DhN1fZQoaAZHQHAbSfHxSYRoB03xAmgIR0CUb55QxesxdX2UKGgGR0BBAoVVPva2aAdL32gIR0CUdETsIE8rdX2UKGgGR0A17VnmJWNnaAdL32gIR0CUdRh2nsLOdX2UKGgGR0BJbFKbrkbQaAdL8mgIR0CUdVzyz5XVdX2UKGgGR0BwaM2gnMMaaAdNiAFoCEdAlHXJV0cOsnV9lChoBkdAZYRhm5DqnmgHTegDaAhHQJR2OreZXuF1fZQoaAZHQE47cxCY1HhoB0uqaAhHQJR3aaZx7zF1fZQoaAZHQG7Szt1IRRNoB026AWgIR0CUfIqnFYMfdX2UKGgGR0BJ5lt8/lhgaAdLy2gIR0CUfxUeMhoudX2UKGgGR0Be3Pq5byH3aAdN6ANoCEdAlIAdgrpaBHV9lChoBkdAcAmMDfWMCWgHTasCaAhHQJSAQ/B3zMB1fZQoaAZHQHEkMJY1YQtoB03hAmgIR0CUgJGt6ol2dX2UKGgGR0BsEXkRzzVdaAdNeAFoCEdAlIEgiV0LdHV9lChoBkdAURlVQyhzvWgHS7xoCEdAlIrCp71Iy3V9lChoBkdAQ/RHNHH3lGgHS+VoCEdAlJ/0RaouPHV9lChoBkdAcgVI2OyVwGgHTasCaAhHQJSgWDDjzZp1fZQoaAZHQHABS+g13t9oB03OAWgIR0CUoGlSjxkNdX2UKGgGR0BgVH/rB0p3aAdN6ANoCEdAlKEzY7JXAHV9lChoBkdAcLtvYe1a4mgHTcoBaAhHQJShjsC1Z1V1fZQoaAZHQF7Yl5WzWwxoB03oA2gIR0CUobBpHqeLdX2UKGgGR0Bwekgntv4uaAdNfwFoCEdAlKMAw482aXV9lChoBkdAcS+zmfXf7GgHTV0BaAhHQJSj2bobGWF1fZQoaAZHQHAGY5xR2r5oB00/AmgIR0CUpC54nndPdX2UKGgGR0BiG4aHbh3raAdN6ANoCEdAlKU9z8xbjnV9lChoBkdAOPsqBmPHUGgHS95oCEdAlKek96kZaXV9lChoBkdAckoq//NqxmgHTdQBaAhHQJSo/hybQTp1fZQoaAZHQG0yP420iQloB038AWgIR0CUqrLNwBHTdX2UKGgGR0BpVgPPLPldaAdN6ANoCEdAlKyItDlYEHV9lChoBkdAb0lZTyauwGgHTVEBaAhHQJSwrlvIfbN1fZQoaAZHQHDb096kZaVoB02fAWgIR0CUsVE5QxetdX2UKGgGR0Bwtpl7MPjGaAdNSwFoCEdAlLN5WRzRyHV9lChoBkdAcXquKGcnV2gHTdADaAhHQJS0i/pMYdh1fZQoaAZHQHCke4LCvX9oB03RAWgIR0CUtWUypJf6dX2UKGgGR0BxkbB3zMA4aAdNmgFoCEdAlLW3T3IuG3V9lChoBkdAWRyBz3h4uGgHTegDaAhHQJS2lflZHNJ1fZQoaAZHQG+92Vu76HloB00aAmgIR0CUuu+eOGTLdX2UKGgGR0BtlFm16Vt5aAdNlAFoCEdAlLtLdepn6HV9lChoBkdAb45maH9FWmgHTX8CaAhHQJS9XqfOD8N1fZQoaAZHQG93qdQO4G5oB02yAWgIR0CUvzUXHim3dX2UKGgGR0BwUYQWepXIaAdNNQFoCEdAlL+N2HLzPXV9lChoBkdAQYUMAmzBymgHS/RoCEdAlMA9VFQVK3V9lChoBkdARBinxaxHG2gHS+JoCEdAlMA8Co0hvHV9lChoBkdAcgrGmk30gGgHTc0CaAhHQJTA915jYqZ1fZQoaAZHQHAwAiRnvlVoB03iAmgIR0CUwTJcPe54dX2UKGgGR0BycSBXjlxPaAdNUgFoCEdAlMWr83uNP3V9lChoBkdAczwDD0lJH2gHTa0BaAhHQJTHOV0Lc9J1fZQoaAZHQHF+slw97nhoB00QAmgIR0CUyWHpbD/EdX2UKGgGR0BwewLRa5f/aAdNDwNoCEdAlMrhuXNTtXV9lChoBkdAcAsIfbKzRmgHTWQBaAhHQJTLGJrLyMF1fZQoaAZHQDWklolD4QBoB00KAWgIR0CUy3f2bobGdX2UKGgGR0BwPsDbJwKjaAdNJAFoCEdAlMv6sU7CBXV9lChoBkdAX47ZRKpT/GgHTegDaAhHQJTMDSpiqhl1ZS4="}, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "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": 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-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 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
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8309716306c9bcba55068e3b9a1f0c5cb1e74bb52feaa2e0fc09e985c510ee4d
|
3 |
+
size 148064
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,54 +4,54 @@
|
|
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._abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
-
"num_timesteps":
|
25 |
"_total_timesteps": 1000000,
|
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'>",
|
38 |
-
":serialized:": "
|
39 |
},
|
40 |
"_last_original_obs": null,
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
-
"_current_progress_remaining": -0.
|
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'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
-
"_n_updates":
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "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",
|
@@ -76,7 +76,7 @@
|
|
76 |
"dtype": "int64",
|
77 |
"_np_random": null
|
78 |
},
|
79 |
-
"n_envs":
|
80 |
"n_steps": 1024,
|
81 |
"gamma": 0.999,
|
82 |
"gae_lambda": 0.98,
|
|
|
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 0x7b9448194940>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b94481949d0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b9448194a60>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b9448194af0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7b9448194b80>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7b9448194c10>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7b9448194ca0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b9448194d30>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7b9448194dc0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b9448194e50>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b9448194ee0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7b9448194f70>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7b9448123180>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 1015808,
|
25 |
"_total_timesteps": 1000000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1720997113961289202,
|
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'>",
|
38 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
39 |
},
|
40 |
"_last_original_obs": null,
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -0.015808000000000044,
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "gAWVMwwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQGGHWvB7/n6MAWyUTegDjAF0lEdAk+/3SSeRP3V9lChoBkdAYqM95hScb2gHTegDaAhHQJPx0pz90ih1fZQoaAZHQG98I6bONYNoB01bAmgIR0CT9Gw2l2vCdX2UKGgGR0BgJ2grYoRaaAdN6ANoCEdAk/jSGi5/b3V9lChoBkdAZ0ar/82rGWgHTegDaAhHQJP+0uJ1q351fZQoaAZHQGGB3vhIe5poB03oA2gIR0CT/xliSaE0dX2UKGgGR0BoGlCswL3LaAdN6ANoCEdAlABROLzf8HV9lChoBkdAZof7fpD/l2gHTegDaAhHQJQVv/JeVs11fZQoaAZHQHGWCtA9mpVoB02AAWgIR0CUGU9lmOENdX2UKGgGR0BmLCJ66asqaAdN6ANoCEdAlBr0TcqOLnV9lChoBkdAYSqsIVuaW2gHTegDaAhHQJQbEZEUj9p1fZQoaAZHQHDOiwnpjc5oB031AWgIR0CUG5QVbiZOdX2UKGgGR0Bx2iXsw+MZaAdNDgNoCEdAlBxNZJTVD3V9lChoBkdAcXOMKkVN6GgHTVUDaAhHQJQhMafjCHh1fZQoaAZHQHGNO1fE4vNoB01jA2gIR0CUIUuh9LHudX2UKGgGR0Bn9UXBP9DQaAdN6ANoCEdAlCOgi7kGRnV9lChoBkdAYjqSNfgJkWgHTegDaAhHQJQnTLaEi+t1fZQoaAZHQGt9wXZXdTJoB02oAmgIR0CULgoNNJvpdX2UKGgGR0BHSl7dBSk1aAdNAAFoCEdAlDQWvKU3XXV9lChoBkdAZDo8NhE0BWgHTegDaAhHQJQ0I2606YF1fZQoaAZHQG5f9vCMxXZoB021AWgIR0CUNR6kIomYdX2UKGgGR0By93rKNhmYaAdNnQJoCEdAlDYcPz4DcXV9lChoBkdAbBxkGRmseWgHTdYBaAhHQJQ2Rmf5DZ11fZQoaAZHQHB5AGW2PT5oB01bAWgIR0CUNuYrrgO0dX2UKGgGR0ByQirzXjEOaAdNkAFoCEdAlDmI7Rv3rXV9lChoBkdAaGD+d9Ujs2gHTegDaAhHQJQ5rBbfP5Z1fZQoaAZHQHD52uDBdldoB02rAmgIR0CUPs4c3l0YdX2UKGgGR0BMolqzqrzYaAdL3WgIR0CUQAIre67NdX2UKGgGR0Bws9IoVmBfaAdNhgNoCEdAlEBAv+OwPnV9lChoBkdAUNHdgv114mgHS+doCEdAlEFkV8CxNnV9lChoBkdAbdpHdXT3I2gHTbQDaAhHQJRCFJHy3Ct1fZQoaAZHQG1pKziS7oVoB01YA2gIR0CUQ1A4XGfgdX2UKGgGR0AkEALiMo+faAdLrmgIR0CUXWOpKjBVdX2UKGgGR0BBYlTFVDKHaAdL72gIR0CUXsK+zt1IdX2UKGgGR0BxlHRtxdY5aAdNTwJoCEdAlF+KmTC+DnV9lChoBkdAbm8H6/IsAmgHTbECaAhHQJRfnqcEvCd1fZQoaAZHQE+FuEVWS2ZoB0vdaAhHQJRh5Bw++uh1fZQoaAZHQHBPKpLmITJoB032AWgIR0CUYssQd0aIdX2UKGgGR0Bk2NHz6JqJaAdN6ANoCEdAlGNmVE/jbXV9lChoBkdAbLV4Oc2BKGgHTUUCaAhHQJRkCaCtihF1fZQoaAZHQGjDnpB5X2doB03oA2gIR0CUZKe/Ho5hdX2UKGgGR0BvpybYsd1daAdNTQJoCEdAlGh/BSDRMXV9lChoBkdAcXSqMm4RVmgHTdMBaAhHQJRqNSS/0ul1fZQoaAZHQEKUXAM2FWZoB0utaAhHQJRqTrNW2gF1fZQoaAZHQG9/sSCe2/loB039AWgIR0CUat9i+cpcdX2UKGgGR0BvttOGj9GaaAdNOQFoCEdAlGup/9YOlXV9lChoBkdAO8d0ihWYGGgHS+BoCEdAlGvrqdH2AXV9lChoBkdAcd2fv4M4LmgHTTYDaAhHQJRvY8W9DhN1fZQoaAZHQHAbSfHxSYRoB03xAmgIR0CUb55QxesxdX2UKGgGR0BBAoVVPva2aAdL32gIR0CUdETsIE8rdX2UKGgGR0A17VnmJWNnaAdL32gIR0CUdRh2nsLOdX2UKGgGR0BJbFKbrkbQaAdL8mgIR0CUdVzyz5XVdX2UKGgGR0BwaM2gnMMaaAdNiAFoCEdAlHXJV0cOsnV9lChoBkdAZYRhm5DqnmgHTegDaAhHQJR2OreZXuF1fZQoaAZHQE47cxCY1HhoB0uqaAhHQJR3aaZx7zF1fZQoaAZHQG7Szt1IRRNoB026AWgIR0CUfIqnFYMfdX2UKGgGR0BJ5lt8/lhgaAdLy2gIR0CUfxUeMhoudX2UKGgGR0Be3Pq5byH3aAdN6ANoCEdAlIAdgrpaBHV9lChoBkdAcAmMDfWMCWgHTasCaAhHQJSAQ/B3zMB1fZQoaAZHQHEkMJY1YQtoB03hAmgIR0CUgJGt6ol2dX2UKGgGR0BsEXkRzzVdaAdNeAFoCEdAlIEgiV0LdHV9lChoBkdAURlVQyhzvWgHS7xoCEdAlIrCp71Iy3V9lChoBkdAQ/RHNHH3lGgHS+VoCEdAlJ/0RaouPHV9lChoBkdAcgVI2OyVwGgHTasCaAhHQJSgWDDjzZp1fZQoaAZHQHABS+g13t9oB03OAWgIR0CUoGlSjxkNdX2UKGgGR0BgVH/rB0p3aAdN6ANoCEdAlKEzY7JXAHV9lChoBkdAcLtvYe1a4mgHTcoBaAhHQJShjsC1Z1V1fZQoaAZHQF7Yl5WzWwxoB03oA2gIR0CUobBpHqeLdX2UKGgGR0Bwekgntv4uaAdNfwFoCEdAlKMAw482aXV9lChoBkdAcS+zmfXf7GgHTV0BaAhHQJSj2bobGWF1fZQoaAZHQHAGY5xR2r5oB00/AmgIR0CUpC54nndPdX2UKGgGR0BiG4aHbh3raAdN6ANoCEdAlKU9z8xbjnV9lChoBkdAOPsqBmPHUGgHS95oCEdAlKek96kZaXV9lChoBkdAckoq//NqxmgHTdQBaAhHQJSo/hybQTp1fZQoaAZHQG0yP420iQloB038AWgIR0CUqrLNwBHTdX2UKGgGR0BpVgPPLPldaAdN6ANoCEdAlKyItDlYEHV9lChoBkdAb0lZTyauwGgHTVEBaAhHQJSwrlvIfbN1fZQoaAZHQHDb096kZaVoB02fAWgIR0CUsVE5QxetdX2UKGgGR0Bwtpl7MPjGaAdNSwFoCEdAlLN5WRzRyHV9lChoBkdAcXquKGcnV2gHTdADaAhHQJS0i/pMYdh1fZQoaAZHQHCke4LCvX9oB03RAWgIR0CUtWUypJf6dX2UKGgGR0BxkbB3zMA4aAdNmgFoCEdAlLW3T3IuG3V9lChoBkdAWRyBz3h4uGgHTegDaAhHQJS2lflZHNJ1fZQoaAZHQG+92Vu76HloB00aAmgIR0CUuu+eOGTLdX2UKGgGR0BtlFm16Vt5aAdNlAFoCEdAlLtLdepn6HV9lChoBkdAb45maH9FWmgHTX8CaAhHQJS9XqfOD8N1fZQoaAZHQG93qdQO4G5oB02yAWgIR0CUvzUXHim3dX2UKGgGR0BwUYQWepXIaAdNNQFoCEdAlL+N2HLzPXV9lChoBkdAQYUMAmzBymgHS/RoCEdAlMA9VFQVK3V9lChoBkdARBinxaxHG2gHS+JoCEdAlMA8Co0hvHV9lChoBkdAcgrGmk30gGgHTc0CaAhHQJTA915jYqZ1fZQoaAZHQHAwAiRnvlVoB03iAmgIR0CUwTJcPe54dX2UKGgGR0BycSBXjlxPaAdNUgFoCEdAlMWr83uNP3V9lChoBkdAczwDD0lJH2gHTa0BaAhHQJTHOV0Lc9J1fZQoaAZHQHF+slw97nhoB00QAmgIR0CUyWHpbD/EdX2UKGgGR0BwewLRa5f/aAdNDwNoCEdAlMrhuXNTtXV9lChoBkdAcAsIfbKzRmgHTWQBaAhHQJTLGJrLyMF1fZQoaAZHQDWklolD4QBoB00KAWgIR0CUy3f2bobGdX2UKGgGR0BwPsDbJwKjaAdNJAFoCEdAlMv6sU7CBXV9lChoBkdAX47ZRKpT/GgHTegDaAhHQJTMDSpiqhl1ZS4="
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
+
"_n_updates": 248,
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "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",
|
|
|
76 |
"dtype": "int64",
|
77 |
"_np_random": null
|
78 |
},
|
79 |
+
"n_envs": 16,
|
80 |
"n_steps": 1024,
|
81 |
"gamma": 0.999,
|
82 |
"gae_lambda": 0.98,
|
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 88362
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78862685508394d7f44b8bfcf2b270a80ceb51200da4f28403ea4adf5c8cda37
|
3 |
size 88362
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43762
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a133645e7af170398b84132becdd86e7584d0b30fba498e2b0b8cbb0b5cb9a2
|
3 |
size 43762
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
-
- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC
|
2 |
- Python: 3.10.12
|
3 |
- Stable-Baselines3: 2.0.0a5
|
4 |
- PyTorch: 2.3.0+cu121
|
|
|
1 |
+
- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
|
2 |
- Python: 3.10.12
|
3 |
- Stable-Baselines3: 2.0.0a5
|
4 |
- PyTorch: 2.3.0+cu121
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 228.81507034140446, "std_reward": 62.62177238956464, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-14T23:10:39.647737"}
|