patilrohan94's picture
Uploading PPO LunarLanderv2 agent
1e70e2e
raw
history blame
10.6 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 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 0x7f55a5245000>",
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f55a5245090>",
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f55a5245120>",
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f55a52451b0>",
"_build": "<function ActorCriticPolicy._build at 0x7f55a5245240>",
"forward": "<function ActorCriticPolicy.forward at 0x7f55a52452d0>",
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f55a5245360>",
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f55a52453f0>",
"_predict": "<function ActorCriticPolicy._predict at 0x7f55a5245480>",
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f55a5245510>",
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f55a52455a0>",
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f55a5245630>",
"__abstractmethods__": "frozenset()",
"_abc_impl": "<_abc._abc_data object at 0x7f55a523a5c0>"
},
"verbose": 1,
"policy_kwargs": {},
"num_timesteps": 16384,
"_total_timesteps": 100.0,
"_num_timesteps_at_start": 0,
"seed": null,
"action_noise": null,
"start_time": 1683378997592620749,
"learning_rate": 0.0003,
"tensorboard_log": "./ppo_lunar_lander_v2/",
"lr_schedule": {
":type:": "<class 'function'>",
":serialized:": "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"
},
"_last_obs": {
":type:": "<class 'numpy.ndarray'>",
":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAH3jgT5Zy4Q/krKzPh8ZoL7gxYQ+PloUvQAAAAAAAAAAGuEVPpKepj8lMwU/pd6QvnEKJT7y1I4+AAAAAAAAAABzigw+qfoRvK2H+70nVQa9YT3ZPIs4X70AAIA/AACAPxDBsD7kqAo/0MWLvaXwkr4YCe09ElJzvQAAAAAAAAAAgG6YPSl0V7q6tIo6ifQbNt3fAjskzZ65AACAPwAAgD/z3sy9e/6MupqgsTs3s8I4s2lWu7UXWboAAIA/AACAP2aemT0UmoW6eJHztnXmyLH7HO46waoONgAAgD8AAIA/prGfPkf3ST8e7qi9Qw2Svifytz2lh0W9AAAAAAAAAAAzkOa84Xq4uN3d+7OvvJuvX59xu7GEsTMAAIA/AACAP5oygL1ygqM/hEiyvny+mb5boem8kQG/vQAAAAAAAAAAAJzWu8Jroz/gt/e8xXiLvpaX1bzifyk+AAAAAAAAAAAAuky9V6jePvO4Fb3cYWK+SPxlvWWu5j0AAAAAAAAAAMBorz325F262ITYO2Os6DcLusM5hoFnNgAAAAAAAAAAJlDSvWp4tD9Jnbi+kbx3vlL3LL74xV++AAAAAAAAAAANnR++CkauPyN8Ib4/v4u+xb1uvgXoIz0AAAAAAAAAALNYjj1S4xQ+eyRPvXlTir7j2Do9xQdRvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="
},
"_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": -162.84,
"_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": 252,
"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,
"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:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
"n": 4,
"_shape": [],
"dtype": "int64",
"_np_random": null
},
"n_envs": 16
}