Commit
·
fb7d512
1
Parent(s):
a776605
Third version of 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 +20 -20
- 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: 270.71 +/- 14.37
|
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 0x7f23910b2700>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f23910b2790>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f23910b2820>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f23910b28b0>", "_build": "<function ActorCriticPolicy._build at 0x7f23910b2940>", "forward": "<function ActorCriticPolicy.forward at 0x7f23910b29d0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f23910b2a60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f23910b2af0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f23910b2b80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f23910b2c10>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f23910b2ca0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f23910b2d30>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f23910b4fc0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 32768, "_total_timesteps": 20000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1678597073273245053, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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": -0.6384000000000001, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVHRAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMId50N+WeWa8CUhpRSlIwBbJRLUowBdJRHQDthMPBi1At1fZQoaAZoCWgPQwhrLGFtjA0dwJSGlFKUaBVLXGgWR0A7ZV0Lc9GJdX2UKGgGaAloD0MIpItNKwXPZ8CUhpRSlGgVS1NoFkdAO2mg8KXv6XV9lChoBmgJaA9DCE+Q2O4eWl/AlIaUUpRoFUtqaBZHQDtsV8CxNZh1fZQoaAZoCWgPQwgepRKe0LBmwJSGlFKUaBVLVGgWR0A7cAuIyj59dX2UKGgGaAloD0MIIZIhx9ZiVcCUhpRSlGgVS0NoFkdAO3Rcu8K5TnV9lChoBmgJaA9DCHbhB+fTE2DAlIaUUpRoFUtRaBZHQDt6flIVdop1fZQoaAZoCWgPQwg8MIDwoQRTwJSGlFKUaBVLUWgWR0A7faLn9vS/dX2UKGgGaAloD0MIC170FaTEWsCUhpRSlGgVS0poFkdAO4nOGCZnc3V9lChoBmgJaA9DCOePaW0aVlnAlIaUUpRoFUtiaBZHQDuMVHnU2DR1fZQoaAZoCWgPQwiCkCxggoNuwJSGlFKUaBVLdGgWR0A7kKcd5prUdX2UKGgGaAloD0MIJQSr6uVvUcCUhpRSlGgVSz5oFkdAO5SjYZl4DHV9lChoBmgJaA9DCOfib3uC4VnAlIaUUpRoFUtmaBZHQDuYsqaw2VF1fZQoaAZoCWgPQwgpCYm0DSdgwJSGlFKUaBVLfGgWR0A7nzu4PPLQdX2UKGgGaAloD0MIU8vW+iKFWsCUhpRSlGgVSzloFkdAO6jfBN21UnV9lChoBmgJaA9DCIyd8BKcRF7AlIaUUpRoFUtnaBZHQDuuyIHkcS51fZQoaAZoCWgPQwh2pPrOr7hnwJSGlFKUaBVLWGgWR0A7u2FWXC0odX2UKGgGaAloD0MIqp7MP3ovYsCUhpRSlGgVS2ZoFkdAO776xgRbr3V9lChoBmgJaA9DCMeePZcps2DAlIaUUpRoFUs7aBZHQDvHzcynDSB1fZQoaAZoCWgPQwgqqKj6leBTwJSGlFKUaBVLP2gWR0A70pg1FYuCdX2UKGgGaAloD0MIQnkfR/ONbcCUhpRSlGgVS01oFkdAO9VZ1V5rxnV9lChoBmgJaA9DCAq7KHrg5mfAlIaUUpRoFUtuaBZHQDvWvbGm1pl1fZQoaAZoCWgPQwjuYMQ+gTdgwJSGlFKUaBVLXmgWR0A72fk3juKGdX2UKGgGaAloD0MIqrUwC+29YcCUhpRSlGgVS39oFkdAO9zEzfrKNnV9lChoBmgJaA9DCLFuvDuyaW7AlIaUUpRoFUuFaBZHQDvmcpb2USt1fZQoaAZoCWgPQwh5rYTuEit9wJSGlFKUaBVLfGgWR0A79D5TIeYEdX2UKGgGaAloD0MIBfwaSQLbZcCUhpRSlGgVS2poFkdAO/Tspobn5nV9lChoBmgJaA9DCPj9mxcnA17AlIaUUpRoFUthaBZHQDv4+/xlQMx1fZQoaAZoCWgPQwhxkXu6OgNqwJSGlFKUaBVLpGgWR0A8Du3+dbxFdX2UKGgGaAloD0MIQ1N2+sHpZsCUhpRSlGgVS19oFkdAPA5X6qKgqXV9lChoBmgJaA9DCKCnAYMkfW3AlIaUUpRoFUtraBZHQDwTpaA4GUx1fZQoaAZoCWgPQwijO4idKb10wJSGlFKUaBVLeWgWR0A8FqslsxfwdX2UKGgGaAloD0MIWWsotRchWMCUhpRSlGgVS0VoFkdAPByKWLP2PHV9lChoBmgJaA9DCHAmpgsxNGjAlIaUUpRoFUtRaBZHQDwjshPj4pN1fZQoaAZoCWgPQwh7wac5eb9hwJSGlFKUaBVLVWgWR0A8JWtU4rBkdX2UKGgGaAloD0MINh0B3CxHZcCUhpRSlGgVS09oFkdAPCl67dznzXV9lChoBmgJaA9DCHmu78NBKGLAlIaUUpRoFUtcaBZHQDwwo3Jgb6x1fZQoaAZoCWgPQwiyTL9EvB9dwJSGlFKUaBVLUWgWR0A8NOB19v0idX2UKGgGaAloD0MIk5BI2/hlXsCUhpRSlGgVS3xoFkdAPDqFmFrVOXV9lChoBmgJaA9DCMe44uKo11zAlIaUUpRoFUtQaBZHQDxBAOavzOJ1fZQoaAZoCWgPQwg4vvbMUoJxwJSGlFKUaBVLfmgWR0A8RLFn7HhkdX2UKGgGaAloD0MIGeYEbfJdbsCUhpRSlGgVS49oFkdAPEmPHT7VKHV9lChoBmgJaA9DCD7rGi0Hw1jAlIaUUpRoFUs/aBZHQDxf7sOXmeV1fZQoaAZoCWgPQwhJ2o0+Zv9gwJSGlFKUaBVLUmgWR0A8Yc580DU3dX2UKGgGaAloD0MIBRiWP5+QfcCUhpRSlGgVS3JoFkdAPGG9YfW+XnV9lChoBmgJaA9DCIJUih2Nz13AlIaUUpRoFUtQaBZHQDxjBVMmF8J1fZQoaAZoCWgPQwiobi7+tmtdwJSGlFKUaBVLOmgWR0A8Z11W8yvcdX2UKGgGaAloD0MIWpwxzAmgXcCUhpRSlGgVS0FoFkdAPIIw22oegnV9lChoBmgJaA9DCKpE2VvKBmfAlIaUUpRoFUtfaBZHQDyD2QGOdXl1fZQoaAZoCWgPQwjpYtNKIZVXwJSGlFKUaBVLdmgWR0A8g/IKc/dJdX2UKGgGaAloD0MISrN5HIZKasCUhpRSlGgVS5BoFkdAPIcpobn5i3V9lChoBmgJaA9DCKEsfH2tm2DAlIaUUpRoFUtiaBZHQDyK6kIomXx1fZQoaAZoCWgPQwhWurvOhmlXwJSGlFKUaBVLUWgWR0A8jIf8uSOjdX2UKGgGaAloD0MIQzwSLw9uesCUhpRSlGgVS29oFkdAPIwVKwpvxnV9lChoBmgJaA9DCMnk1M5wo3XAlIaUUpRoFUuLaBZHQDyX4oJAt4B1fZQoaAZoCWgPQwiI9rGC3+xSwJSGlFKUaBVLYWgWR0A8pbpu/DcedX2UKGgGaAloD0MIJhsPttgWc8CUhpRSlGgVS1toFkdAPLy5d4Vym3V9lChoBmgJaA9DCHqPM03YF2XAlIaUUpRoFUtzaBZHQDy6raM72ct1fZQoaAZoCWgPQwgY0At3LsFRwJSGlFKUaBVLOmgWR0A8vgpjMFEBdX2UKGgGaAloD0MI2e2zykx4UcCUhpRSlGgVS49oFkdAPMETpPhybXV9lChoBmgJaA9DCD0NGCR9RVrAlIaUUpRoFUtBaBZHQDzCjj7yhBZ1fZQoaAZoCWgPQwjlf/J3bzZiwJSGlFKUaBVLZGgWR0A8xxsVLzwudX2UKGgGaAloD0MI9FMcB96LZsCUhpRSlGgVS2FoFkdAPMjGo73fynV9lChoBmgJaA9DCDvj++LS6XXAlIaUUpRoFUtvaBZHQDzRLK3d9Dx1fZQoaAZoCWgPQwiOBvAWyLBrwJSGlFKUaBVLeGgWR0A82ezUqhDgdX2UKGgGaAloD0MIOkAwRw/NY8CUhpRSlGgVS2FoFkdAPOpL/S6UaHV9lChoBmgJaA9DCOaUgJiEwmDAlIaUUpRoFUtraBZHQDzsu27Wd3B1fZQoaAZoCWgPQwg3T3XIzQ5fwJSGlFKUaBVLcGgWR0A88EPlMh5gdX2UKGgGaAloD0MIg8E1d/SEZcCUhpRSlGgVS2VoFkdAPO39R77bc3V9lChoBmgJaA9DCFSthVlo1lTAlIaUUpRoFUtDaBZHQDz+/Dcdo391fZQoaAZoCWgPQwhlxAWgUZpXwJSGlFKUaBVLeWgWR0A8//DtPYWddX2UKGgGaAloD0MIUvNV8rGfYMCUhpRSlGgVS2xoFkdAPQ6O938n/nV9lChoBmgJaA9DCAzNdRrpWm3AlIaUUpRoFUt5aBZHQD0NDu0CzTp1fZQoaAZoCWgPQwgMzXUaaZtYwJSGlFKUaBVLTWgWR0A9EwDeTFERdX2UKGgGaAloD0MIP8kdNpFRZsCUhpRSlGgVS1poFkdAPRPKuB+WnnV9lChoBmgJaA9DCILK+PeZ8mzAlIaUUpRoFUtlaBZHQD0ghIOH3111fZQoaAZoCWgPQwi9UwH3PJpewJSGlFKUaBVLRGgWR0A9Kxzq8lHCdX2UKGgGaAloD0MIbwwBwLE2X8CUhpRSlGgVS29oFkdAPSzyOJcgQ3V9lChoBmgJaA9DCPN0riglbCjAlIaUUpRoFUtraBZHQD0wd/8VHnV1fZQoaAZoCWgPQwguWKoLeHtbwJSGlFKUaBVLg2gWR0A9QWD6Fds0dX2UKGgGaAloD0MIQgddwqGcXsCUhpRSlGgVS1poFkdAPUKcurZJ1HV9lChoBmgJaA9DCDJYcao1+GHAlIaUUpRoFUt3aBZHQD1D4Glhw2l1fZQoaAZoCWgPQwivQspPqj1TwJSGlFKUaBVLc2gWR0A9R6JqIrOJdX2UKGgGaAloD0MICYhJuJAMXcCUhpRSlGgVSzxoFkdAPUch1Tzd13V9lChoBmgJaA9DCMKFPIIbaFjAlIaUUpRoFUtJaBZHQD1Ug3cYZVJ1fZQoaAZoCWgPQwgZARWOIMthwJSGlFKUaBVLbWgWR0A9WD8LronsdX2UKGgGaAloD0MI628JwD/iV8CUhpRSlGgVS0doFkdAPVb2L5ylvnV9lChoBmgJaA9DCNSeknNi8mXAlIaUUpRoFUuAaBZHQD1ormQr+YN1fZQoaAZoCWgPQwithsQ9Fq9uwJSGlFKUaBVLYmgWR0A9cP5YYBNmdX2UKGgGaAloD0MIhzYAGxA4c8CUhpRSlGgVS3poFkdAPXWFBY3eenV9lChoBmgJaA9DCOMan8l+gGfAlIaUUpRoFUtPaBZHQD14E7nxJ/Z1fZQoaAZoCWgPQwjjUpW2uGRdwJSGlFKUaBVLS2gWR0A9eYao/A0sdX2UKGgGaAloD0MI9SudD89uPMCUhpRSlGgVS0doFkdAPYaUA1ejVXV9lChoBmgJaA9DCEzhQbPr72fAlIaUUpRoFUs6aBZHQD2PXwsoUi91fZQoaAZoCWgPQwjgSnZshEphwJSGlFKUaBVLS2gWR0A9j2NvOyE+dX2UKGgGaAloD0MIBDqTNlXvV8CUhpRSlGgVSz9oFkdAPZI7JW/8EXV9lChoBmgJaA9DCOoDyTuHuEHAlIaUUpRoFUuaaBZHQD2T8VHnU2F1fZQoaAZoCWgPQwjQ7/s3LwJiwJSGlFKUaBVLamgWR0A9k/wAlv61dX2UKGgGaAloD0MI+SzPgzvdY8CUhpRSlGgVS3hoFkdAPZTpPhybQXV9lChoBmgJaA9DCBlW8UbmxWbAlIaUUpRoFUthaBZHQD2kDcM3IdV1ZS4="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 8, "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, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
|
|
|
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 0x7f7fb64ccca0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7fb64ccd30>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7fb64ccdc0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7fb64cce50>", "_build": "<function ActorCriticPolicy._build at 0x7f7fb64ccee0>", "forward": "<function ActorCriticPolicy.forward at 0x7f7fb64ccf70>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f7fb64ce040>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7fb64ce0d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f7fb64ce160>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7fb64ce1f0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7fb64ce280>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7fb64ce310>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f7fb64d00c0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1678598539534361107, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "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, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
|
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 sha256:0ff2a093b743a07317a319b0ebafffb9858c138a9c88dd9b3f9b0d9ddb64e656
|
3 |
+
size 147417
|
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._abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
@@ -43,12 +43,12 @@
|
|
43 |
"_np_random": null
|
44 |
},
|
45 |
"n_envs": 16,
|
46 |
-
"num_timesteps":
|
47 |
-
"_total_timesteps":
|
48 |
"_num_timesteps_at_start": 0,
|
49 |
"seed": null,
|
50 |
"action_noise": null,
|
51 |
-
"start_time":
|
52 |
"learning_rate": 0.0003,
|
53 |
"tensorboard_log": null,
|
54 |
"lr_schedule": {
|
@@ -57,7 +57,7 @@
|
|
57 |
},
|
58 |
"_last_obs": {
|
59 |
":type:": "<class 'numpy.ndarray'>",
|
60 |
-
":serialized:": "
|
61 |
},
|
62 |
"_last_episode_starts": {
|
63 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -67,16 +67,16 @@
|
|
67 |
"_episode_num": 0,
|
68 |
"use_sde": false,
|
69 |
"sde_sample_freq": -1,
|
70 |
-
"_current_progress_remaining": -0.
|
71 |
"ep_info_buffer": {
|
72 |
":type:": "<class 'collections.deque'>",
|
73 |
-
":serialized:": "
|
74 |
},
|
75 |
"ep_success_buffer": {
|
76 |
":type:": "<class 'collections.deque'>",
|
77 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
78 |
},
|
79 |
-
"_n_updates":
|
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 0x7f7fb64ccca0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7fb64ccd30>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7fb64ccdc0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7fb64cce50>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f7fb64ccee0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f7fb64ccf70>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f7fb64ce040>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7fb64ce0d0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f7fb64ce160>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7fb64ce1f0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7fb64ce280>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7fb64ce310>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f7fb64d00c0>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
43 |
"_np_random": null
|
44 |
},
|
45 |
"n_envs": 16,
|
46 |
+
"num_timesteps": 1015808,
|
47 |
+
"_total_timesteps": 1000000,
|
48 |
"_num_timesteps_at_start": 0,
|
49 |
"seed": null,
|
50 |
"action_noise": null,
|
51 |
+
"start_time": 1678598539534361107,
|
52 |
"learning_rate": 0.0003,
|
53 |
"tensorboard_log": null,
|
54 |
"lr_schedule": {
|
|
|
57 |
},
|
58 |
"_last_obs": {
|
59 |
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "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"
|
61 |
},
|
62 |
"_last_episode_starts": {
|
63 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
67 |
"_episode_num": 0,
|
68 |
"use_sde": false,
|
69 |
"sde_sample_freq": -1,
|
70 |
+
"_current_progress_remaining": -0.015808000000000044,
|
71 |
"ep_info_buffer": {
|
72 |
":type:": "<class 'collections.deque'>",
|
73 |
+
":serialized:": "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"
|
74 |
},
|
75 |
"ep_success_buffer": {
|
76 |
":type:": "<class 'collections.deque'>",
|
77 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
78 |
},
|
79 |
+
"_n_updates": 248,
|
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 87929
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12983aab557dd51cd7740984749f84049fc0bbd20a1a2ba1722cc6c0cfa36029
|
3 |
size 87929
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43393
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44394e78abbc1a43965bec56f93716ec5d02a8c6a45e9ccd50e53eb4d5d322c6
|
3 |
size 43393
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 270.71309338169533, "std_reward": 14.371572623945427, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-12T05:44:57.641102"}
|