File size: 14,595 Bytes
893b919 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 |
{
"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 0x7fd957a07f80>",
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd957a0f050>",
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd957a0f0e0>",
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd957a0f170>",
"_build": "<function ActorCriticPolicy._build at 0x7fd957a0f200>",
"forward": "<function ActorCriticPolicy.forward at 0x7fd957a0f290>",
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd957a0f320>",
"_predict": "<function ActorCriticPolicy._predict at 0x7fd957a0f3b0>",
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd957a0f440>",
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd957a0f4d0>",
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd957a0f560>",
"__abstractmethods__": "frozenset()",
"_abc_impl": "<_abc_data object at 0x7fd957a4fbd0>"
},
"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": 2015232,
"_total_timesteps": 2000000,
"_num_timesteps_at_start": 0,
"seed": null,
"action_noise": null,
"start_time": 1652191039.0019844,
"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": -0.007616000000000067,
"ep_info_buffer": {
":type:": "<class 'collections.deque'>",
":serialized:": "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"
},
"ep_success_buffer": {
":type:": "<class 'collections.deque'>",
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
},
"_n_updates": 492,
"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
} |