kingducks's picture
first MLP PPO commit of HF
82019fe
{
"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 0x796ac1281630>",
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x796ac12816c0>",
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x796ac1281750>",
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x796ac12817e0>",
"_build": "<function ActorCriticPolicy._build at 0x796ac1281870>",
"forward": "<function ActorCriticPolicy.forward at 0x796ac1281900>",
"extract_features": "<function ActorCriticPolicy.extract_features at 0x796ac1281990>",
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x796ac1281a20>",
"_predict": "<function ActorCriticPolicy._predict at 0x796ac1281ab0>",
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x796ac1281b40>",
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x796ac1281bd0>",
"predict_values": "<function ActorCriticPolicy.predict_values at 0x796ac1281c60>",
"__abstractmethods__": "frozenset()",
"_abc_impl": "<_abc._abc_data object at 0x796ac1273140>"
},
"verbose": 1,
"policy_kwargs": {},
"num_timesteps": 1000448,
"_total_timesteps": 1000000,
"_num_timesteps_at_start": 0,
"seed": null,
"action_noise": null,
"start_time": 1689636116258543620,
"learning_rate": 0.0003,
"tensorboard_log": null,
"_last_obs": {
":type:": "<class 'numpy.ndarray'>",
":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAE3L5j2zmQs/Z8KPvQ2dkb72l7Y8WLUHvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.00044800000000000395,
"_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": 3908,
"observation_space": {
":type:": "<class 'gymnasium.spaces.box.Box'>",
":serialized:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=",
"dtype": "float32",
"bounded_below": "[ True True True True True True True True]",
"bounded_above": "[ True True True True True True True True]",
"_shape": [
8
],
"low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
"high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
"low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
"high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
"_np_random": null
},
"action_space": {
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
"n": "4",
"start": "0",
"_shape": [],
"dtype": "int64",
"_np_random": null
},
"n_envs": 1,
"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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"
}
}