forked from carla-simulator/rllib-integration
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathppo_default_config_597d2de3.txt
189 lines (189 loc) · 7.09 KB
/
ppo_default_config_597d2de3.txt
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
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
"observation_space": null,
"action_space": null,
"env_task_fn": null,
"render_env": false,
"clip_rewards": null,
"normalize_actions": true,
"clip_actions": false,
"disable_env_checking": false,
"_is_atari": null,
"auto_wrap_old_gym_envs": true,
"action_mask_key": "action_mask",
"env_runner_cls": null,
"num_envs_per_worker": 1,
"sample_collector": {
"_type": "CLOUDPICKLE_FALLBACK",
"value": "80059551000000000000008c357261792e726c6c69622e6576616c756174696f6e2e636f6c6c6563746f72732e73696d706c655f6c6973745f636f6c6c6563746f72948c1353696d706c654c697374436f6c6c6563746f729493942e"
},
"sample_async": false,
"enable_connectors": true,
"update_worker_filter_stats": true,
"use_worker_filter_stats": true,
"rollout_fragment_length": "auto",
"batch_mode": "truncate_episodes",
"remote_worker_envs": false,
"remote_env_batch_wait_ms": 0,
"validate_workers_after_construction": true,
"preprocessor_pref": "deepmind",
"observation_filter": "NoFilter",
"compress_observations": false,
"enable_tf1_exec_eagerly": false,
"sampler_perf_stats_ema_coef": null,
"gamma": 1,
"lr": 5e-06,
"grad_clip": null,
"grad_clip_by": "global_norm",
"train_batch_size": 2048,
"model": {
"_disable_preprocessor_api": false,
"_disable_action_flattening": false,
"fcnet_hiddens": [
256,
256
],
"fcnet_activation": "tanh",
"conv_filters": null,
"conv_activation": "relu",
"post_fcnet_hiddens": [],
"post_fcnet_activation": "relu",
"free_log_std": false,
"no_final_linear": false,
"vf_share_layers": false,
"use_lstm": false,
"max_seq_len": 20,
"lstm_cell_size": 256,
"lstm_use_prev_action": false,
"lstm_use_prev_reward": false,
"_time_major": false,
"use_attention": false,
"attention_num_transformer_units": 1,
"attention_dim": 64,
"attention_num_heads": 1,
"attention_head_dim": 32,
"attention_memory_inference": 50,
"attention_memory_training": 50,
"attention_position_wise_mlp_dim": 32,
"attention_init_gru_gate_bias": 2.0,
"attention_use_n_prev_actions": 0,
"attention_use_n_prev_rewards": 0,
"framestack": true,
"dim": 84,
"grayscale": false,
"zero_mean": true,
"custom_model": null,
"custom_model_config": {},
"custom_action_dist": null,
"custom_preprocessor": null,
"encoder_latent_dim": null,
"always_check_shapes": false,
"lstm_use_prev_action_reward": -1,
"_use_default_native_models": -1
},
"optimizer": {},
"max_requests_in_flight_per_sampler_worker": 2,
"_learner_class": null,
"_enable_learner_api": true,
"explore": true,
"exploration_config": {},
"algorithm_config_overrides_per_module": {},
"policy_map_capacity": 100,
"policy_mapping_fn": {
"_type": "CLOUDPICKLE_FALLBACK",
"value": "80059557000000000000008c257261792e726c6c69622e616c676f726974686d732e616c676f726974686d5f636f6e666967948c29416c676f726974686d436f6e6669672e44454641554c545f504f4c4943595f4d415050494e475f464e9493942e"
},
"policies_to_train": null,
"policy_states_are_swappable": false,
"observation_fn": null,
"count_steps_by": "env_steps",
"input_config": {},
"actions_in_input_normalized": false,
"postprocess_inputs": false,
"shuffle_buffer_size": 0,
"output": null,
"output_config": {},
"output_compress_columns": [
"obs",
"new_obs"
],
"output_max_file_size": 67108864,
"offline_sampling": false,
"evaluation_interval": null,
"evaluation_duration": 10,
"evaluation_duration_unit": "episodes",
"evaluation_sample_timeout_s": 180.0,
"evaluation_parallel_to_training": false,
"evaluation_config": null,
"off_policy_estimation_methods": {},
"ope_split_batch_by_episode": true,
"evaluation_num_workers": 0,
"always_attach_evaluation_results": false,
"enable_async_evaluation": false,
"in_evaluation": false,
"sync_filters_on_rollout_workers_timeout_s": 60.0,
"keep_per_episode_custom_metrics": false,
"metrics_episode_collection_timeout_s": 60.0,
"metrics_num_episodes_for_smoothing": 100,
"min_time_s_per_iteration": null,
"min_train_timesteps_per_iteration": 0,
"min_sample_timesteps_per_iteration": 0,
"export_native_model_files": false,
"checkpoint_trainable_policies_only": false,
"logger_creator": null,
"logger_config": null,
"log_level": "WARN",
"log_sys_usage": true,
"fake_sampler": false,
"seed": null,
"ignore_worker_failures": false,
"recreate_failed_workers": false,
"max_num_worker_restarts": 1000,
"delay_between_worker_restarts_s": 60.0,
"restart_failed_sub_environments": false,
"num_consecutive_worker_failures_tolerance": 100,
"worker_health_probe_timeout_s": 60,
"worker_restore_timeout_s": 1800,
"rl_module_spec": {
"_type": "CLOUDPICKLE_FALLBACK",
"value": "80059536010000000000008c227261792e726c6c69622e636f72652e726c5f6d6f64756c652e726c5f6d6f64756c65948c1753696e676c654167656e74524c4d6f64756c65537065639493942981947d94288c0c6d6f64756c655f636c617373948c327261792e726c6c69622e616c676f726974686d732e70706f2e746f7263682e70706f5f746f7263685f726c5f6d6f64756c65948c1050504f546f726368524c4d6f64756c659493948c116f62736572766174696f6e5f7370616365944e8c0c616374696f6e5f7370616365944e8c116d6f64656c5f636f6e6669675f64696374944e8c0d636174616c6f675f636c617373948c247261792e726c6c69622e616c676f726974686d732e70706f2e70706f5f636174616c6f67948c0a50504f436174616c6f679493948c0f6c6f61645f73746174655f70617468944e75622e"
},
"_enable_rl_module_api": true,
"_AlgorithmConfig__prior_exploration_config": {
"type": "StochasticSampling"
},
"_tf_policy_handles_more_than_one_loss": false,
"_disable_preprocessor_api": false,
"_disable_action_flattening": false,
"_disable_execution_plan_api": true,
"_disable_initialize_loss_from_dummy_batch": false,
"simple_optimizer": false,
"policy_map_cache": -1,
"worker_cls": -1,
"synchronize_filters": -1,
"replay_sequence_length": null,
"lr_schedule": null,
"use_critic": true,
"use_gae": true,
"use_kl_loss": true,
"kl_coeff": 0.2,
"kl_target": 0.01,
"sgd_minibatch_size": 128,
"num_sgd_iter": 30,
"shuffle_sequences": true,
"vf_loss_coeff": 1.0,
"entropy_coeff": 0.0,
"entropy_coeff_schedule": null,
"clip_param": 0.3,
"vf_clip_param": 10.0,
"vf_share_layers": -1,
"__stdout_file__": null,
"__stderr_file__": null,
"lambda": 1.0,
"input": "sampler",
"policies": {
"default_policy": [
null,
null,
null,
null
]
},