format37 commited on
Commit
764abf9
1 Parent(s): 4fdbc10

Upload PPO LunarLander-v2 trained agent

Browse files
README.md CHANGED
@@ -10,7 +10,7 @@ model-index:
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
- value: -123.87 +/- 19.22
14
  name: mean_reward
15
  task:
16
  type: reinforcement-learning
 
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
+ value: 274.99 +/- 20.06
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 0x7ff9ed024820>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff9ed0248b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff9ed024940>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff9ed0249d0>", "_build": "<function ActorCriticPolicy._build at 0x7ff9ed024a60>", "forward": "<function ActorCriticPolicy.forward at 0x7ff9ed024af0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff9ed024b80>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff9ed024c10>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff9ed024ca0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff9ed024d30>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff9ed024dc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ff9ed0256c0>"}, "verbose": 0, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu", "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": 1, "num_timesteps": 5120, "_total_timesteps": 5000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652289955.5168335, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAJIDxL6x9NA+BdBKv5Pdk7+HB9E+/P8JPgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.02400000000000002, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVxQgAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMI2EroLonvYcCUhpRSlIwBbJRLaYwBdJRHP/yA8B+4LCx1fZQoaAZoCWgPQwjxSScSTCVdwJSGlFKUaBVLX2gWRz/97teD3/PxdX2UKGgGaAloD0MIbSBdbFoQWsCUhpRSlGgVS3FoFkc//5d5Y5ksjHV9lChoBmgJaA9DCChiEcPO6HLAlIaUUpRoFUtqaBZHQACh4Uvf0mN1fZQoaAZoCWgPQwjAdcWMcCJ3wJSGlFKUaBVLaWgWR0ABwFcIJJGwdX2UKGgGaAloD0MIu9OdJx6EdsCUhpRSlGgVS2xoFkdAAx5gw482aXV9lChoBmgJaA9DCM6pZAAo+mPAlIaUUpRoFUtOaBZHQAPO1F6Rhc91fZQoaAZoCWgPQwhBguLHmL8yQJSGlFKUaBVLimgWR0AE5bt7a7EpdX2UKGgGaAloD0MI8BXdes0iZsCUhpRSlGgVS3doFkdABcnJkoWpInV9lChoBmgJaA9DCAwG19zRKFvAlIaUUpRoFUtDaBZHQAZ5wGW2PT51fZQoaAZoCWgPQwiX/iWpTMdRwJSGlFKUaBVLPmgWR0AG7jkuHvc8dX2UKGgGaAloD0MIW5iFdk6+YsCUhpRSlGgVS3VoFkdAB8jTrmhdt3V9lChoBmgJaA9DCPHydK4oeVrAlIaUUpRoFUtEaBZHQAhHOB19v0h1fZQoaAZoCWgPQwj1nsppjzB0wJSGlFKUaBVLa2gWR0AJaYu01IiDdX2UKGgGaAloD0MImX6JeOsKWsCUhpRSlGgVS1FoFkdACn4Ju2qkunV9lChoBmgJaA9DCAtioGtfhVXAlIaUUpRoFUuBaBZHQAuOQ6p5u651fZQoaAZoCWgPQwgPf03WqJdpwJSGlFKUaBVLWmgWR0AMNgUlAu7IdX2UKGgGaAloD0MISKMCJ9tfccCUhpRSlGgVS35oFkdADSOOKfnOjnV9lChoBmgJaA9DCJKvBFJiJVnAlIaUUpRoFUtZaBZHQA3LOzIFNcp1fZQoaAZoCWgPQwgZINEEiqpXwJSGlFKUaBVLamgWR0AOkMkQf6oEdX2UKGgGaAloD0MIEHf1KrJibsCUhpRSlGgVS3hoFkdAD6FN+LFXJnV9lChoBmgJaA9DCJWdflAXn1rAlIaUUpRoFUteaBZHQBAmGh24d6t1fZQoaAZoCWgPQwh/Z3v0BmlkwJSGlFKUaBVLd2gWR0AQl0A93bEhdX2UKGgGaAloD0MIjPhOzHrJYsCUhpRSlGgVS2xoFkdAEQZIQOFxn3V9lChoBmgJaA9DCDuOHyoNhGXAlIaUUpRoFUtsaBZHQBGbIYFaB7N1fZQoaAZoCWgPQwi1/pYAfONgwJSGlFKUaBVLOWgWR0ARzvG6wt8NdX2UKGgGaAloD0MIdoh/2FIOacCUhpRSlGgVS1RoFkdAEh7wrlNlAnV9lChoBmgJaA9DCJ8fRgjPB3nAlIaUUpRoFUtRaBZHQBJoBq9Gqgh1fZQoaAZoCWgPQwi2vHK9bYRlwJSGlFKUaBVLc2gWR0AS1Bw++ueSdX2UKGgGaAloD0MIqtctAmMgWsCUhpRSlGgVS0JoFkdAExMFUyYXwnV9lChoBmgJaA9DCG3KFd7lD2LAlIaUUpRoFUtVaBZHQBNlqJuVHFx1fZQoaAZoCWgPQwikOEcdnbVmwJSGlFKUaBVLYmgWR0AT4RywOe8PdX2UKGgGaAloD0MIWI6QgTycXsCUhpRSlGgVS2doFkdAFEUfxMFlkHV9lChoBmgJaA9DCAIrhxbZTlbAlIaUUpRoFUt7aBZHQBUDUmUnogV1fZQoaAZoCWgPQwgZVYZxt0NmwJSGlFKUaBVLYmgWR0AVnIbOu7pWdX2UKGgGaAloD0MI9wFIbeJWXcCUhpRSlGgVS1ZoFkdAFfGVAzHjqHV9lChoBmgJaA9DCAr19BF4O2TAlIaUUpRoFUteaBZHQBZPHcUM5Ot1fZQoaAZoCWgPQwgyy54EtvhgwJSGlFKUaBVLTWgWR0AWnr4WUKRddX2UKGgGaAloD0MIDFcHQNw9YsCUhpRSlGgVS2FoFkdAFv8ohIOH33V9lChoBmgJaA9DCLSvPEhPpF7AlIaUUpRoFUtWaBZHQBdSCz1K5Cp1fZQoaAZoCWgPQwhMN4lBYEl+wJSGlFKUaBVLXmgWR0AXs84gieNDdX2UKGgGaAloD0MI8YCyKdeKZcCUhpRSlGgVS0JoFkdAF/LbHp8neHV9lChoBmgJaA9DCJp5ck2BHlfAlIaUUpRoFUteaBZHQBhoDs+mm+F1fZQoaAZoCWgPQwjZXDXPkQxqwJSGlFKUaBVLX2gWR0AYydJ8OTaCdX2UKGgGaAloD0MIFVgAUwZHbMCUhpRSlGgVS3toFkdAGXqZc9nscHV9lChoBmgJaA9DCDVgkPTp2W7AlIaUUpRoFUtNaBZHQBnGAPNFBpp1fZQoaAZoCWgPQwhR2ht8YWNfwJSGlFKUaBVLQmgWR0AaAs9SuQp4dX2UKGgGaAloD0MIurw5XKvlb8CUhpRSlGgVS3VoFkdAGm46wMYuTXV9lChoBmgJaA9DCElm9Q63b3jAlIaUUpRoFUtxaBZHQBrZj6N2ki51fZQoaAZoCWgPQwhortNIS7pgwJSGlFKUaBVLPGgWR0AbEEmplz2fdX2UKGgGaAloD0MIa9RDNLpqWMCUhpRSlGgVS1doFkdAG2AvL5h0AHV9lChoBmgJaA9DCLxbWaKzfFnAlIaUUpRoFUtbaBZHQBu3fZVXFLp1fZQoaAZoCWgPQwj+utOdJ3ZYwJSGlFKUaBVLQ2gWR0Ab9onKGL1mdWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 20, "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": 1024, "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-5.13.0-40-generic-x86_64-with-glibc2.31 #45~20.04.1-Ubuntu SMP Mon Apr 4 09:38:31 UTC 2022", "Python": "3.9.12", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu102", "GPU Enabled": "True", "Numpy": "1.22.3", "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 0x7fac9a13c820>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fac9a13c8b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fac9a13c940>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fac9a13c9d0>", "_build": "<function ActorCriticPolicy._build at 0x7fac9a13ca60>", "forward": "<function ActorCriticPolicy.forward at 0x7fac9a13caf0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fac9a13cb80>", "_predict": "<function ActorCriticPolicy._predict at 0x7fac9a13cc10>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fac9a13cca0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fac9a13cd30>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fac9a13cdc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fac9a77f5c0>"}, "verbose": 0, "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": 1, "num_timesteps": 25001984, "_total_timesteps": 25000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652309258.506598, "learning_rate": 0.00025, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAADO+Nj7YGZ0+AMbzvUeYkL6RyKU9gg0BugAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -7.935999999997279e-05, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 122080, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 1024, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.13.0-40-generic-x86_64-with-glibc2.31 #45~20.04.1-Ubuntu SMP Mon Apr 4 09:38:31 UTC 2022", "Python": "3.9.12", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu102", "GPU Enabled": "True", "Numpy": "1.22.3", "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:f3c254fef95fbbc800b6bf03ba9ce97cf5b098d76139209ae665727bc855bb5b
3
- size 140922
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9c7968343b1b444cf8b3e07a0c10a1bad0b604a0355792f9f0a88fa0d3bce88
3
+ size 143547
ppo-LunarLander-v2/data CHANGED
@@ -4,19 +4,19 @@
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 0x7ff9ed024820>",
8
- "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff9ed0248b0>",
9
- "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff9ed024940>",
10
- "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff9ed0249d0>",
11
- "_build": "<function ActorCriticPolicy._build at 0x7ff9ed024a60>",
12
- "forward": "<function ActorCriticPolicy.forward at 0x7ff9ed024af0>",
13
- "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff9ed024b80>",
14
- "_predict": "<function ActorCriticPolicy._predict at 0x7ff9ed024c10>",
15
- "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff9ed024ca0>",
16
- "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff9ed024d30>",
17
- "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff9ed024dc0>",
18
  "__abstractmethods__": "frozenset()",
19
- "_abc_impl": "<_abc._abc_data object at 0x7ff9ed0256c0>"
20
  },
21
  "verbose": 0,
22
  "policy_kwargs": {},
@@ -42,21 +42,21 @@
42
  "_np_random": null
43
  },
44
  "n_envs": 1,
45
- "num_timesteps": 5120,
46
- "_total_timesteps": 5000,
47
  "_num_timesteps_at_start": 0,
48
  "seed": null,
49
  "action_noise": null,
50
- "start_time": 1652289955.5168335,
51
- "learning_rate": 0.0003,
52
  "tensorboard_log": null,
53
  "lr_schedule": {
54
  ":type:": "<class 'function'>",
55
- ":serialized:": "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"
56
  },
57
  "_last_obs": {
58
  ":type:": "<class 'numpy.ndarray'>",
59
- ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAJIDxL6x9NA+BdBKv5Pdk7+HB9E+/P8JPgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
60
  },
61
  "_last_episode_starts": {
62
  ":type:": "<class 'numpy.ndarray'>",
@@ -66,24 +66,24 @@
66
  "_episode_num": 0,
67
  "use_sde": false,
68
  "sde_sample_freq": -1,
69
- "_current_progress_remaining": -0.02400000000000002,
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": 20,
79
- "n_steps": 1024,
80
- "gamma": 0.999,
81
- "gae_lambda": 0.98,
82
- "ent_coef": 0.01,
83
  "vf_coef": 0.5,
84
  "max_grad_norm": 0.5,
85
  "batch_size": 1024,
86
- "n_epochs": 4,
87
  "clip_range": {
88
  ":type:": "<class 'function'>",
89
  ":serialized:": "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"
 
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 0x7fac9a13c820>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fac9a13c8b0>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fac9a13c940>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fac9a13c9d0>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7fac9a13ca60>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7fac9a13caf0>",
13
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fac9a13cb80>",
14
+ "_predict": "<function ActorCriticPolicy._predict at 0x7fac9a13cc10>",
15
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fac9a13cca0>",
16
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fac9a13cd30>",
17
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fac9a13cdc0>",
18
  "__abstractmethods__": "frozenset()",
19
+ "_abc_impl": "<_abc._abc_data object at 0x7fac9a77f5c0>"
20
  },
21
  "verbose": 0,
22
  "policy_kwargs": {},
 
42
  "_np_random": null
43
  },
44
  "n_envs": 1,
45
+ "num_timesteps": 25001984,
46
+ "_total_timesteps": 25000000,
47
  "_num_timesteps_at_start": 0,
48
  "seed": null,
49
  "action_noise": null,
50
+ "start_time": 1652309258.506598,
51
+ "learning_rate": 0.00025,
52
  "tensorboard_log": null,
53
  "lr_schedule": {
54
  ":type:": "<class 'function'>",
55
+ ":serialized:": "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"
56
  },
57
  "_last_obs": {
58
  ":type:": "<class 'numpy.ndarray'>",
59
+ ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAADO+Nj7YGZ0+AMbzvUeYkL6RyKU9gg0BugAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
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": -7.935999999997279e-05,
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": 122080,
79
+ "n_steps": 2048,
80
+ "gamma": 0.99,
81
+ "gae_lambda": 0.95,
82
+ "ent_coef": 0.0,
83
  "vf_coef": 0.5,
84
  "max_grad_norm": 0.5,
85
  "batch_size": 1024,
86
+ "n_epochs": 10,
87
  "clip_range": {
88
  ":type:": "<class 'function'>",
89
  ":serialized:": "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"
ppo-LunarLander-v2/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97524fcfe29d19c6d7435f53512b0cba9661baaa7148e9dba76d88cfcd5f13cb
3
- size 84829
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0812bb8095a83b6c52e95f10c40eb510f8b2c9e2464531d8ee5e6546b4fcb4e6
3
+ size 84893
ppo-LunarLander-v2/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41d1a8d0bb9f773bf59c9132cd25c993b42287814677b0167bb217ca61c1074c
3
  size 43201
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae67ed0b4599f2528e4e648fc7c5d3524ffbf15d6d0788dbba53bf390e2c457f
3
  size 43201
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79777bfb3a8ccaec98fa9837c0f9fcf78142fc993e605371fe8aecd437e013ef
3
- size 172760
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c4e83eb5cd96e13b6a7c8f63edee79448c5ada5602ce6cb463710a2ec3fb8d0
3
+ size 192703
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": -123.8688810897991, "std_reward": 19.21930683731547, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T22:52:29.860525"}
 
1
+ {"mean_reward": 274.9912011429598, "std_reward": 20.06397431951631, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-12T11:10:17.806335"}