fmcurti's picture
Increasing training steps, playing with hyperparameters
c1c9b89
raw
history blame
13.9 kB
{
"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 0x7f709f166f80>",
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f709f16f050>",
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f709f16f0e0>",
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f709f16f170>",
"_build": "<function ActorCriticPolicy._build at 0x7f709f16f200>",
"forward": "<function ActorCriticPolicy.forward at 0x7f709f16f290>",
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f709f16f320>",
"_predict": "<function ActorCriticPolicy._predict at 0x7f709f16f3b0>",
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f709f16f440>",
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f709f16f4d0>",
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f709f16f560>",
"__abstractmethods__": "frozenset()",
"_abc_impl": "<_abc_data object at 0x7f709f13e390>"
},
"verbose": 1,
"policy_kwargs": {
":type:": "<class 'dict'>",
":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=",
"optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>",
"optimizer_kwargs": {
"alpha": 0.99,
"eps": 1e-05,
"weight_decay": 0
}
},
"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": 1651770197.7187119,
"learning_rate": 0.0007,
"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": 31,
"n_steps": 2048,
"gamma": 0.99,
"gae_lambda": 0.98,
"ent_coef": 0.01,
"vf_coef": 0.5,
"max_grad_norm": 0.5,
"normalize_advantage": false
}