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 +23 -23
- 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 +2 -2
- results.json +1 -1
README.md
CHANGED
@@ -10,7 +10,7 @@ model-index:
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
-
value:
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
+
value: 287.72 +/- 17.30
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x7f3d83656560>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3d836565f0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3d83656680>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3d83656710>", "_build": "<function ActorCriticPolicy._build at 0x7f3d836567a0>", "forward": "<function ActorCriticPolicy.forward at 0x7f3d83656830>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3d836568c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f3d83656950>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3d836569e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3d83656a70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3d83656b00>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f3d83695c60>"}, "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": 5013504, "_total_timesteps": 5000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652242323.5009809, "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": -0.0027007999999999477, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVHhAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMImL9C5oq9cUCUhpRSlIwBbJRLyowBdJRHQLSOUGUOd5J1fZQoaAZoCWgPQwg504TtZx1zQJSGlFKUaBVL52gWR0C0jnbEHdGidX2UKGgGaAloD0MIach4lAp6cUCUhpRSlGgVS9xoFkdAtI6VPk7wKHV9lChoBmgJaA9DCNejcD3KJ3BAlIaUUpRoFUvNaBZHQLSOny8BdUt1fZQoaAZoCWgPQwhXW7G/bK1xQJSGlFKUaBVL1mgWR0C0jqkkSmIkdX2UKGgGaAloD0MInBa86CtCSkCUhpRSlGgVS6VoFkdAtI6/UWl/IHV9lChoBmgJaA9DCNtpa0SwBXFAlIaUUpRoFUu9aBZHQLSOyQlruYx1fZQoaAZoCWgPQwhnRj8aDt1yQJSGlFKUaBVL9GgWR0C0jtERWcSXdX2UKGgGaAloD0MIArnEkQfjckCUhpRSlGgVS+RoFkdAtI8NwT/Q0HV9lChoBmgJaA9DCFM/bypSpXNAlIaUUpRoFUv5aBZHQLSPGSV4X411fZQoaAZoCWgPQwiutmJ/WdhuQJSGlFKUaBVL0GgWR0C0jxeIl+mWdX2UKGgGaAloD0MI++jUlQ9CcECUhpRSlGgVS9RoFkdAtI9RqdpZfXV9lChoBmgJaA9DCP6ZQXxglnFAlIaUUpRoFUvcaBZHQLSPdkTYdyV1fZQoaAZoCWgPQwh8fEJ2XiBxQJSGlFKUaBVL4mgWR0C0j3o0EX+EdX2UKGgGaAloD0MIONxHbs1rckCUhpRSlGgVS95oFkdAtI+Z47ihnXV9lChoBmgJaA9DCCnrNxPTnW5AlIaUUpRoFUvSaBZHQLSPv9GI9DB1fZQoaAZoCWgPQwh24Qfnk4NxQJSGlFKUaBVNcwFoFkdAtI/cn4O+ZnV9lChoBmgJaA9DCGSQuwhTN3BAlIaUUpRoFUvXaBZHQLSP8lum78N1fZQoaAZoCWgPQwjw+WGEsCVzQJSGlFKUaBVLymgWR0C0kAM+aBqcdX2UKGgGaAloD0MIDeAtkKCscECUhpRSlGgVS9VoFkdAtJANgb6xgXV9lChoBmgJaA9DCJzgm6bPMHFAlIaUUpRoFUvVaBZHQLSQIFn7Hhl1fZQoaAZoCWgPQwg2kZkLXCFzQJSGlFKUaBVLyWgWR0C0kDJVbRnfdX2UKGgGaAloD0MIYD5ZMdxXcUCUhpRSlGgVS+RoFkdAtJbbqkdmx3V9lChoBmgJaA9DCOI5W0Bo53FAlIaUUpRoFUviaBZHQLSW4ehf0Ep1fZQoaAZoCWgPQwivCWmNAdVwQJSGlFKUaBVLz2gWR0C0lwwwK0D2dX2UKGgGaAloD0MIoWXdP5ZUckCUhpRSlGgVS9toFkdAtJcXTAnDznV9lChoBmgJaA9DCB4Wak0zPHJAlIaUUpRoFUvkaBZHQLSXLzOoo/l1fZQoaAZoCWgPQwgHsp5aPWdxQJSGlFKUaBVL4WgWR0C0l2DASFoMdX2UKGgGaAloD0MIYYicvl62ckCUhpRSlGgVS9JoFkdAtJdnZAY51nV9lChoBmgJaA9DCG/XS1PEhXFAlIaUUpRoFUvfaBZHQLSXf9Oymhx1fZQoaAZoCWgPQwgIsMivH5ZwQJSGlFKUaBVL1WgWR0C0l48qril0dX2UKGgGaAloD0MI6nk3FhQIckCUhpRSlGgVS8ZoFkdAtJeaTlkpZ3V9lChoBmgJaA9DCMZun1UmEnNAlIaUUpRoFUvcaBZHQLSX2ZVGTcJ1fZQoaAZoCWgPQwhWf4RhQHJvQJSGlFKUaBVL0WgWR0C0l9v1DjR2dX2UKGgGaAloD0MI4ExMF2KTckCUhpRSlGgVS8NoFkdAtJfwbwSamXV9lChoBmgJaA9DCM1bdR2qXXJAlIaUUpRoFUvVaBZHQLSX+189fTl1fZQoaAZoCWgPQwgMHxFTolJwQJSGlFKUaBVL6GgWR0C0mBFwHZ9NdX2UKGgGaAloD0MIaAWGrK4McECUhpRSlGgVS9toFkdAtJgqMzdk8XV9lChoBmgJaA9DCEX2QZaFFHFAlIaUUpRoFUvIaBZHQLSYK66reZZ1fZQoaAZoCWgPQwjR56OM+GhzQJSGlFKUaBVL5WgWR0C0mFEZJkGzdX2UKGgGaAloD0MIEcR5OIGYc0CUhpRSlGgVS9BoFkdAtJhpdD6WPnV9lChoBmgJaA9DCJxpwvYTDXJAlIaUUpRoFUvQaBZHQLSYgFX7tRh1fZQoaAZoCWgPQwgNx/MZEDd0QJSGlFKUaBVL9mgWR0C0mJhLPD51dX2UKGgGaAloD0MIi4nNx/VYckCUhpRSlGgVS8hoFkdAtJirbO/tY3V9lChoBmgJaA9DCJSI8C+CbHNAlIaUUpRoFUvRaBZHQLSYs9b5dnl1fZQoaAZoCWgPQwgVWABThopvQJSGlFKUaBVLzmgWR0C0mOSXQdCFdX2UKGgGaAloD0MIyAp+GyLeckCUhpRSlGgVS9hoFkdAtJjcyk9EC3V9lChoBmgJaA9DCJVjsrj/uW5AlIaUUpRoFUvhaBZHQLSY+XzDn/11fZQoaAZoCWgPQwgxJv29FN5uQJSGlFKUaBVLv2gWR0C0mQtpyp71dX2UKGgGaAloD0MIuMoTCHtickCUhpRSlGgVS7loFkdAtJkWE/Spi3V9lChoBmgJaA9DCH0kJT0M33JAlIaUUpRoFUvNaBZHQLSZISDh99d1fZQoaAZoCWgPQwgSv2INVzNxQJSGlFKUaBVLy2gWR0C0mTxceKbbdX2UKGgGaAloD0MIghspW2TZcECUhpRSlGgVS7NoFkdAtJlGAkLQX3V9lChoBmgJaA9DCOPe/IbJJXBAlIaUUpRoFUvMaBZHQLSZUZ9d/rl1fZQoaAZoCWgPQwj6QzNPLgpvQJSGlFKUaBVL0WgWR0C0mXJpnHvMdX2UKGgGaAloD0MIq+l6omu3cUCUhpRSlGgVS8doFkdAtJmMIHC40HV9lChoBmgJaA9DCBL6mXqdl3BAlIaUUpRoFUvcaBZHQLSZyyIHkcV1fZQoaAZoCWgPQwiu8gTCTkxyQJSGlFKUaBVLumgWR0C0meAmReTndX2UKGgGaAloD0MIwTv59BikckCUhpRSlGgVS91oFkdAtJnlZjhDPXV9lChoBmgJaA9DCOLmVDLAe3JAlIaUUpRoFUvZaBZHQLSZ+TLW7OF1fZQoaAZoCWgPQwjlRSbgVwRyQJSGlFKUaBVLt2gWR0C0mg6bONYKdX2UKGgGaAloD0MIT135LM9XOECUhpRSlGgVS5hoFkdAtJoWVC5VfnV9lChoBmgJaA9DCK1oc5wbrnJAlIaUUpRoFUvjaBZHQLSaG5le4Td1fZQoaAZoCWgPQwj+D7BWrW90QJSGlFKUaBVL1GgWR0C0mjXN9ph4dX2UKGgGaAloD0MIz0vFxvxRckCUhpRSlGgVS9ZoFkdAtJpVoi9qUXV9lChoBmgJaA9DCF5KXTIOpXJAlIaUUpRoFUvSaBZHQLSaXrTpgTh1fZQoaAZoCWgPQwhfYizTLydyQJSGlFKUaBVL4GgWR0C0mn3IdU83dX2UKGgGaAloD0MI8kHPZlXzb0CUhpRSlGgVS8RoFkdAtJp4WsRxtHV9lChoBmgJaA9DCLgf8MDAB3NAlIaUUpRoFUvJaBZHQLSaiR/3Fkx1fZQoaAZoCWgPQwjMzw1N2RNuQJSGlFKUaBVLz2gWR0C0mp2W6bvxdX2UKGgGaAloD0MIER5tHPG3ckCUhpRSlGgVS8BoFkdAtJrDg9/z8XV9lChoBmgJaA9DCPksz4O7dHJAlIaUUpRoFUvpaBZHQLSa7ATIvJ11fZQoaAZoCWgPQwi/1xAcl3VxQJSGlFKUaBVLyGgWR0C0myp/kNnXdX2UKGgGaAloD0MIJ7wEp74LckCUhpRSlGgVS9hoFkdAtJsqvvBrOHV9lChoBmgJaA9DCLlt36N+CXBAlIaUUpRoFUvGaBZHQLSbO+XJHRV1fZQoaAZoCWgPQwi29j5VBTxwQJSGlFKUaBVL0mgWR0C0m2bKq4pddX2UKGgGaAloD0MIU82spQApbkCUhpRSlGgVS/BoFkdAtJtqjpLVWnV9lChoBmgJaA9DCHZxGw3g0nJAlIaUUpRoFUvLaBZHQLSbaVp9JBh1fZQoaAZoCWgPQwgWpYRgFVVxQJSGlFKUaBVLyGgWR0C0m517Qb++dX2UKGgGaAloD0MI4Qoo1NMrc0CUhpRSlGgVS+5oFkdAtJuc51eSjnV9lChoBmgJaA9DCJwzorS3MnJAlIaUUpRoFUvsaBZHQLSbugvDgqF1fZQoaAZoCWgPQwjYR6eu/OpvQJSGlFKUaBVLwWgWR0C0m8uc+aBqdX2UKGgGaAloD0MImzdOCrO7cUCUhpRSlGgVS8toFkdAtJvJsenyeHV9lChoBmgJaA9DCAnE6/oFRnBAlIaUUpRoFUvGaBZHQLSb67Omixp1fZQoaAZoCWgPQwjDmsqicNRzQJSGlFKUaBVL5mgWR0C0m/yRr8BNdX2UKGgGaAloD0MIotCy7h/fcUCUhpRSlGgVS9RoFkdAtJwmx+rlvXV9lChoBmgJaA9DCEVKs3kcGXJAlIaUUpRoFUviaBZHQLScaCZ4Oc51fZQoaAZoCWgPQwjChxItOUxyQJSGlFKUaBVLwWgWR0C0nK+RLbpNdX2UKGgGaAloD0MIrFW7JqRacUCUhpRSlGgVS9doFkdAtJyrqqwQlXV9lChoBmgJaA9DCACN0qX/dXNAlIaUUpRoFUvoaBZHQLScvANG3F11fZQoaAZoCWgPQwjkTBO2H8JxQJSGlFKUaBVL6mgWR0C0nL/hddE9dX2UKGgGaAloD0MIDRr6J7jxbkCUhpRSlGgVS9doFkdAtJzeu6mO2nV9lChoBmgJaA9DCMvVj01ybHNAlIaUUpRoFUvwaBZHQLSdCfFJg9h1fZQoaAZoCWgPQwgU56ij4yNzQJSGlFKUaBVLz2gWR0C0nQh6v7m/dX2UKGgGaAloD0MIqfkq+ZgmcUCUhpRSlGgVS79oFkdAtJ0dtGd7OXV9lChoBmgJaA9DCAVPIVdqrHFAlIaUUpRoFUvOaBZHQLSdJOXE61d1fZQoaAZoCWgPQwjwMsNG2ZdyQJSGlFKUaBVL5mgWR0C0nTFJcxCZdX2UKGgGaAloD0MIRNsxdRe1cUCUhpRSlGgVS8xoFkdAtJ0yMAFPi3V9lChoBmgJaA9DCIGXGTYKsXFAlIaUUpRoFUvRaBZHQLSdWYxtYSx1fZQoaAZoCWgPQwjZsKayKJBzQJSGlFKUaBVL1mgWR0C0nXHVLBbfdWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1224, "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-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x7f6d8db9a950>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6d8db9a9e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6d8db9aa70>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6d8db9ab00>", "_build": "<function ActorCriticPolicy._build at 0x7f6d8db9ab90>", "forward": "<function ActorCriticPolicy.forward at 0x7f6d8db9ac20>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6d8db9acb0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f6d8db9ad40>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6d8db9add0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6d8db9ae60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6d8db9aef0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f6d8dbe78a0>"}, "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:": "gAWVgQAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc2hhcGWUKYwFZHR5cGWUjAVudW1weZRoB5OUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijApfbnBfcmFuZG9tlE51Yi4=", "n": 4, "shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 30015488, "_total_timesteps": 30000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652260749.4011745, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "_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": -0.0005162666666667093, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 7328, "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-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.17.3"}}
|
ppo-LunarLander-v2.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 143984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b8611a7df0fa18b96c58fb6388e116af0d40e4652d6449f1c8a2d5c4a445904
|
3 |
size 143984
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,27 +4,27 @@
|
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
14 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
15 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
16 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
17 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
-
"_abc_impl": "<_abc_data object at
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
23 |
"observation_space": {
|
24 |
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
-
":serialized:": "
|
26 |
"dtype": "float32",
|
27 |
-
"
|
28 |
8
|
29 |
],
|
30 |
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
@@ -35,19 +35,19 @@
|
|
35 |
},
|
36 |
"action_space": {
|
37 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
-
":serialized:": "
|
39 |
"n": 4,
|
40 |
-
"
|
41 |
"dtype": "int64",
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
-
"num_timesteps":
|
46 |
-
"_total_timesteps":
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
-
"start_time":
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
@@ -56,7 +56,7 @@
|
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
-
":serialized:": "
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -66,16 +66,16 @@
|
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
-
"_current_progress_remaining": -0.
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
-
":serialized:": "
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
-
"_n_updates":
|
79 |
"n_steps": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x7f6d8db9a950>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6d8db9a9e0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6d8db9aa70>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6d8db9ab00>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f6d8db9ab90>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f6d8db9ac20>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6d8db9acb0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f6d8db9ad40>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6d8db9add0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6d8db9ae60>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6d8db9aef0>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f6d8dbe78a0>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
23 |
"observation_space": {
|
24 |
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "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",
|
26 |
"dtype": "float32",
|
27 |
+
"shape": [
|
28 |
8
|
29 |
],
|
30 |
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
|
|
35 |
},
|
36 |
"action_space": {
|
37 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "gAWVgQAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc2hhcGWUKYwFZHR5cGWUjAVudW1weZRoB5OUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijApfbnBfcmFuZG9tlE51Yi4=",
|
39 |
"n": 4,
|
40 |
+
"shape": [],
|
41 |
"dtype": "int64",
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
+
"num_timesteps": 30015488,
|
46 |
+
"_total_timesteps": 30000000,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1652260749.4011745,
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
|
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "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"
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.0005162666666667093,
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "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"
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
+
"_n_updates": 7328,
|
79 |
"n_steps": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"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 84893
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d0af67b697e5228cc8906a7c2250a673a2c3983d65426bc8960b545901153d1
|
3 |
size 84893
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43201
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bdd4cdb153a7d9ebe2eaf160383d9b85637004b7ae534e3a20efa9a8d53cf1b
|
3 |
size 43201
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -4,4 +4,4 @@ Stable-Baselines3: 1.5.0
|
|
4 |
PyTorch: 1.11.0+cu113
|
5 |
GPU Enabled: True
|
6 |
Numpy: 1.21.6
|
7 |
-
Gym: 0.
|
|
|
4 |
PyTorch: 1.11.0+cu113
|
5 |
GPU Enabled: True
|
6 |
Numpy: 1.21.6
|
7 |
+
Gym: 0.17.3
|
replay.mp4
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 sha256:45a30a2abb709d4796cb8ee5336e10d1140620d28b52ee75ec068b95ffca409f
|
3 |
+
size 180092
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 287.72486796008684, "std_reward": 17.30213732188768, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T14:15:46.915975"}
|