File size: 16,907 Bytes
70d6612 |
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 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 |
{
"policy_class": {
":type:": "<class 'abc.ABCMeta'>",
":serialized:": "gAWVNwAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnRkMy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu",
"__module__": "stable_baselines3.td3.policies",
"__doc__": "\n Policy class (with both actor and critic) for TD3 to be used with Dict observation spaces.\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 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 :param n_critics: Number of critic networks to create.\n :param share_features_extractor: Whether to share or not the features extractor\n between the actor and the critic (this saves computation time)\n ",
"__init__": "<function MultiInputPolicy.__init__ at 0x7d585e1495a0>",
"__abstractmethods__": "frozenset()",
"_abc_impl": "<_abc._abc_data object at 0x7d585e14c140>"
},
"verbose": 1,
"policy_kwargs": {
"net_arch": [
256,
256,
256
],
"n_critics": 1
},
"num_timesteps": 1000050,
"_total_timesteps": 1000000,
"_num_timesteps_at_start": 0,
"seed": null,
"action_noise": {
":type:": "<class 'stable_baselines3.common.noise.NormalActionNoise'>",
":serialized:": "gAWVMQEAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5ub2lzZZSMEU5vcm1hbEFjdGlvbk5vaXNllJOUKYGUfZQojANfbXWUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLBIWUjAFDlHSUUpSMBl9zaWdtYZRoCCiWIAAAAAAAAACamZmZmZnJP5qZmZmZmck/mpmZmZmZyT+amZmZmZnJP5RoD0sEhZRoE3SUUpSMBl9kdHlwZZRoCowHZmxvYXQzMpSTlHViLg==",
"_mu": "[0. 0. 0. 0.]",
"_sigma": "[0.2 0.2 0.2 0.2]",
"_dtype": "<class 'numpy.float32'>"
},
"start_time": 1709010350043990555,
"learning_rate": 0.001,
"tensorboard_log": "runs/DDPGPandaPickandPlacev3",
"_last_obs": null,
"_last_episode_starts": {
":type:": "<class 'numpy.ndarray'>",
":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
},
"_last_original_obs": {
":type:": "<class 'collections.OrderedDict'>",
":serialized:": "gAWVXwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAAZpTRPUsTgj0K16M8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAAJP4CPvVjED6rFQI+lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWTAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAAAAAAAAZpTRPUsTgj0K16M8AAAAAAAAAIAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlGgOSwFLE4aUaBJ0lFKUdS4=",
"achieved_goal": "[[0.10233383 0.06351336 0.02 ]]",
"desired_goal": "[[0.1279226 0.1410063 0.12703578]]",
"observation": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00 0.0000000e+00 1.0233383e-01\n 6.3513361e-02 2.0000000e-02 0.0000000e+00 -0.0000000e+00\n 0.0000000e+00 0.0000000e+00 0.0000000e+00 0.0000000e+00\n 0.0000000e+00 0.0000000e+00 0.0000000e+00]]"
},
"_episode_num": 20459,
"use_sde": false,
"sde_sample_freq": -1,
"_current_progress_remaining": -5.0000000000105516e-05,
"_stats_window_size": 100,
"ep_info_buffer": {
":type:": "<class 'collections.deque'>",
":serialized:": "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"
},
"ep_success_buffer": {
":type:": "<class 'collections.deque'>",
":serialized:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKImJiYmJiYmJiYmJiYmJiYmJiYmJiYmIiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYllLg=="
},
"_n_updates": 999950,
"observation_space": {
":type:": "<class 'gymnasium.spaces.dict.Dict'>",
":serialized:": "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",
"spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (19,), float32))])",
"_shape": null,
"dtype": null,
"_np_random": null
},
"action_space": {
":type:": "<class 'gymnasium.spaces.box.Box'>",
":serialized:": "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",
"dtype": "float32",
"bounded_below": "[ True True True True]",
"bounded_above": "[ True True True True]",
"_shape": [
4
],
"low": "[-1. -1. -1. -1.]",
"high": "[1. 1. 1. 1.]",
"low_repr": "-1.0",
"high_repr": "1.0",
"_np_random": "Generator(PCG64)"
},
"n_envs": 1,
"buffer_size": 1000000,
"batch_size": 256,
"learning_starts": 100,
"tau": 0.95,
"gamma": 0.99,
"gradient_steps": -1,
"optimize_memory_usage": false,
"replay_buffer_class": {
":type:": "<class 'abc.ABCMeta'>",
":serialized:": "gAWVPwAAAAAAAACMJ3N0YWJsZV9iYXNlbGluZXMzLmhlci5oZXJfcmVwbGF5X2J1ZmZlcpSMD0hlclJlcGxheUJ1ZmZlcpSTlC4=",
"__module__": "stable_baselines3.her.her_replay_buffer",
"__annotations__": "{'env': typing.Optional[stable_baselines3.common.vec_env.base_vec_env.VecEnv]}",
"__doc__": "\n Hindsight Experience Replay (HER) buffer.\n Paper: https://arxiv.org/abs/1707.01495\n\n Replay buffer for sampling HER (Hindsight Experience Replay) transitions.\n\n .. note::\n\n Compared to other implementations, the ``future`` goal sampling strategy is inclusive:\n the current transition can be used when re-sampling.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param env: The training environment\n :param device: PyTorch device\n :param n_envs: Number of parallel environments\n :param optimize_memory_usage: Enable a memory efficient variant\n Disabled for now (see https://github.com/DLR-RM/stable-baselines3/pull/243#discussion_r531535702)\n :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n separately and treat the task as infinite horizon task.\n https://github.com/DLR-RM/stable-baselines3/issues/284\n :param n_sampled_goal: Number of virtual transitions to create per real transition,\n by sampling new goals.\n :param goal_selection_strategy: Strategy for sampling goals for replay.\n One of ['episode', 'final', 'future']\n :param copy_info_dict: Whether to copy the info dictionary and pass it to\n ``compute_reward()`` method.\n Please note that the copy may cause a slowdown.\n False by default.\n ",
"__init__": "<function HerReplayBuffer.__init__ at 0x7d585e14a200>",
"__getstate__": "<function HerReplayBuffer.__getstate__ at 0x7d585e14a290>",
"__setstate__": "<function HerReplayBuffer.__setstate__ at 0x7d585e14a320>",
"set_env": "<function HerReplayBuffer.set_env at 0x7d585e14a3b0>",
"add": "<function HerReplayBuffer.add at 0x7d585e14a440>",
"_compute_episode_length": "<function HerReplayBuffer._compute_episode_length at 0x7d585e14a4d0>",
"sample": "<function HerReplayBuffer.sample at 0x7d585e14a560>",
"_get_real_samples": "<function HerReplayBuffer._get_real_samples at 0x7d585e14a5f0>",
"_get_virtual_samples": "<function HerReplayBuffer._get_virtual_samples at 0x7d585e14a680>",
"_sample_goals": "<function HerReplayBuffer._sample_goals at 0x7d585e14a710>",
"truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x7d585e14a7a0>",
"__abstractmethods__": "frozenset()",
"_abc_impl": "<_abc._abc_data object at 0x7d585e14f400>"
},
"replay_buffer_kwargs": {
":type:": "<class 'dict'>",
":serialized:": "gAWVggAAAAAAAAB9lCiMDm5fc2FtcGxlZF9nb2FslEsEjBdnb2FsX3NlbGVjdGlvbl9zdHJhdGVneZSMLXN0YWJsZV9iYXNlbGluZXMzLmhlci5nb2FsX3NlbGVjdGlvbl9zdHJhdGVneZSMFUdvYWxTZWxlY3Rpb25TdHJhdGVneZSTlEsAhZRSlHUu",
"n_sampled_goal": 4,
"goal_selection_strategy": "GoalSelectionStrategy.FUTURE"
},
"train_freq": {
":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
":serialized:": "gAWVZAAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMB2VwaXNvZGWUhZRSlIaUgZQu"
},
"use_sde_at_warmup": false,
"policy_delay": 1,
"target_noise_clip": 0.0,
"target_policy_noise": 0.1,
"lr_schedule": {
":type:": "<class 'function'>",
":serialized:": "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"
},
"actor_batch_norm_stats": [],
"critic_batch_norm_stats": [],
"actor_batch_norm_stats_target": [],
"critic_batch_norm_stats_target": []
} |