andrewzhang505 commited on
Commit
65ffa8d
1 Parent(s): f147a2f

Upload cfg.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. cfg.json +219 -0
cfg.json ADDED
@@ -0,0 +1,219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "help": false,
3
+ "algo": "APPO",
4
+ "env": "quadrotor_multi",
5
+ "experiment": "01_baseline_multi_drone_see_1111",
6
+ "train_dir": "./train_dir/quad_multi_baseline/baseline_multi_drone_",
7
+ "restart_behavior": "resume",
8
+ "device": "gpu",
9
+ "seed": 1111,
10
+ "num_policies": 1,
11
+ "async_rl": true,
12
+ "serial_mode": false,
13
+ "batched_sampling": true,
14
+ "num_batches_to_accumulate": 8,
15
+ "worker_num_splits": 2,
16
+ "policy_workers_per_policy": 1,
17
+ "max_policy_lag": 100000000,
18
+ "num_workers": 36,
19
+ "num_envs_per_worker": 4,
20
+ "batch_size": 1024,
21
+ "num_batches_per_epoch": 1,
22
+ "num_epochs": 1,
23
+ "rollout": 128,
24
+ "recurrence": 1,
25
+ "shuffle_minibatches": false,
26
+ "gamma": 0.99,
27
+ "reward_scale": 1.0,
28
+ "reward_clip": 1000.0,
29
+ "value_bootstrap": false,
30
+ "normalize_returns": true,
31
+ "exploration_loss_coeff": 0.0,
32
+ "value_loss_coeff": 0.5,
33
+ "kl_loss_coeff": 0.0,
34
+ "exploration_loss": "entropy",
35
+ "gae_lambda": 1.0,
36
+ "ppo_clip_ratio": 0.1,
37
+ "ppo_clip_value": 5.0,
38
+ "with_vtrace": false,
39
+ "vtrace_rho": 1.0,
40
+ "vtrace_c": 1.0,
41
+ "optimizer": "adam",
42
+ "adam_eps": 1e-06,
43
+ "adam_beta1": 0.9,
44
+ "adam_beta2": 0.999,
45
+ "max_grad_norm": 5.0,
46
+ "learning_rate": 0.0001,
47
+ "lr_schedule": "constant",
48
+ "lr_schedule_kl_threshold": 0.008,
49
+ "obs_subtract_mean": 0.0,
50
+ "obs_scale": 1.0,
51
+ "normalize_input": true,
52
+ "normalize_input_keys": null,
53
+ "decorrelate_experience_max_seconds": 0,
54
+ "decorrelate_envs_on_one_worker": true,
55
+ "actor_worker_gpus": [],
56
+ "set_workers_cpu_affinity": true,
57
+ "force_envs_single_thread": false,
58
+ "default_niceness": 0,
59
+ "experiment_summaries_interval": 60,
60
+ "stats_avg": 100,
61
+ "summaries_use_frameskip": true,
62
+ "heartbeat_interval": 10,
63
+ "heartbeat_reporting_interval": 60,
64
+ "train_for_env_steps": 10000000000,
65
+ "train_for_seconds": 10000000000,
66
+ "save_every_sec": 120,
67
+ "keep_checkpoints": 3,
68
+ "load_checkpoint_kind": "latest",
69
+ "save_milestones_sec": 10000,
70
+ "save_best_every_sec": 5,
71
+ "save_best_metric": "reward",
72
+ "save_best_after": 100000,
73
+ "benchmark": false,
74
+ "encoder_type": "mlp",
75
+ "encoder_subtype": "mlp_quads",
76
+ "encoder_custom": "quad_multi_encoder",
77
+ "encoder_extra_fc_layers": 0,
78
+ "hidden_size": 256,
79
+ "nonlinearity": "tanh",
80
+ "policy_initialization": "xavier_uniform",
81
+ "policy_init_gain": 1.0,
82
+ "actor_critic_share_weights": false,
83
+ "adaptive_stddev": false,
84
+ "initial_stddev": 1.0,
85
+ "use_rnn": false,
86
+ "rnn_type": "gru",
87
+ "rnn_num_layers": 1,
88
+ "use_env_info_cache": false,
89
+ "env_gpu_actions": false,
90
+ "env_frameskip": 1,
91
+ "env_framestack": 1,
92
+ "pixel_format": "CHW",
93
+ "use_record_episode_statistics": false,
94
+ "with_wandb": true,
95
+ "wandb_user": null,
96
+ "wandb_project": "sample_factory",
97
+ "wandb_group": null,
98
+ "wandb_job_type": "SF",
99
+ "wandb_tags": [
100
+ "multi"
101
+ ],
102
+ "with_pbt": false,
103
+ "pbt_mix_policies_in_one_env": true,
104
+ "pbt_period_env_steps": 5000000,
105
+ "pbt_start_mutation": 20000000,
106
+ "pbt_replace_fraction": 0.3,
107
+ "pbt_mutation_rate": 0.15,
108
+ "pbt_replace_reward_gap": 0.1,
109
+ "pbt_replace_reward_gap_absolute": 1e-06,
110
+ "pbt_optimize_batch_size": false,
111
+ "pbt_optimize_gamma": false,
112
+ "pbt_target_objective": "true_objective",
113
+ "pbt_perturb_min": 1.05,
114
+ "pbt_perturb_max": 1.5,
115
+ "quads_discretize_actions": -1,
116
+ "quads_clip_input": false,
117
+ "quads_effort_reward": null,
118
+ "quads_episode_duration": 15.0,
119
+ "quads_num_agents": 8,
120
+ "quads_neighbor_hidden_size": 256,
121
+ "quads_neighbor_encoder_type": "attention",
122
+ "quads_collision_reward": 5.0,
123
+ "quads_collision_obstacle_reward": 0.0,
124
+ "quads_settle_reward": 0.0,
125
+ "quads_settle": false,
126
+ "quads_vel_reward_out_range": 0.8,
127
+ "quads_settle_range_meters": 1.0,
128
+ "quads_collision_hitbox_radius": 2.0,
129
+ "quads_collision_falloff_radius": 4.0,
130
+ "quads_collision_smooth_max_penalty": 10.0,
131
+ "neighbor_obs_type": "pos_vel",
132
+ "quads_use_numba": true,
133
+ "quads_obstacle_mode": "no_obstacles",
134
+ "quads_obstacle_num": 0,
135
+ "quads_obstacle_type": "sphere",
136
+ "quads_obstacle_size": 0.0,
137
+ "quads_obstacle_traj": "gravity",
138
+ "quads_local_obs": 6,
139
+ "quads_local_coeff": 1.0,
140
+ "quads_local_metric": "dist",
141
+ "quads_view_mode": "local",
142
+ "quads_adaptive_env": false,
143
+ "quads_mode": "mix",
144
+ "quads_formation": "circle_horizontal",
145
+ "quads_formation_size": 0.0,
146
+ "room_dims": [
147
+ 10,
148
+ 10,
149
+ 10
150
+ ],
151
+ "quads_obs_repr": "xyz_vxyz_R_omega",
152
+ "replay_buffer_sample_prob": 0.75,
153
+ "anneal_collision_steps": 300000000.0,
154
+ "quads_obstacle_obs_mode": "relative",
155
+ "quads_obstacle_hidden_size": 32,
156
+ "quads_collision_obst_smooth_max_penalty": 10.0,
157
+ "quads_obst_penalty_fall_off": 10.0,
158
+ "use_spectral_norm": false,
159
+ "command_line": "--env=quadrotor_multi --train_for_env_steps=1000000000 --algo=APPO --use_rnn=False --num_workers=36 --num_envs_per_worker=4 --learning_rate=0.0001 --ppo_clip_value=5.0 --recurrence=1 --nonlinearity=tanh --actor_critic_share_weights=False --policy_initialization=xavier_uniform --adaptive_stddev=False --with_vtrace=False --max_policy_lag=100000000 --hidden_size=256 --gae_lambda=1.00 --max_grad_norm=5.0 --exploration_loss_coeff=0.0 --rollout=128 --batch_size=1024 --quads_use_numba=True --quads_mode=mix --quads_episode_duration=15.0 --quads_formation_size=0.0 --encoder_custom=quad_multi_encoder --quads_collision_reward=5.0 --quads_neighbor_hidden_size=256 --neighbor_obs_type=pos_vel --quads_settle_reward=0.0 --quads_collision_hitbox_radius=2.0 --quads_collision_falloff_radius=4.0 --quads_local_obs=6 --quads_local_metric=dist --quads_local_coeff=1.0 --quads_num_agents=8 --quads_collision_reward=5.0 --quads_collision_smooth_max_penalty=10.0 --quads_neighbor_encoder_type=attention --replay_buffer_sample_prob=0.75 --anneal_collision_steps=300000000 --train_for_env_steps=10000000000 --num_workers=18 --num_envs_per_worker=8 --quads_num_agents=8 --save_milestones_sec=10000 --async_rl=True --num_batches_to_accumulate=8 --serial_mode=False --batched_sampling=True --normalize_input=True --normalize_returns=True --with_wandb=True --wandb_tags multi --seed=1111 --experiment=01_baseline_multi_drone_see_1111 --train_dir=./train_dir/quad_multi_baseline/baseline_multi_drone_",
160
+ "cli_args": {
161
+ "algo": "APPO",
162
+ "env": "quadrotor_multi",
163
+ "experiment": "01_baseline_multi_drone_see_1111",
164
+ "train_dir": "./train_dir/quad_multi_baseline/baseline_multi_drone_",
165
+ "seed": 1111,
166
+ "async_rl": true,
167
+ "serial_mode": false,
168
+ "batched_sampling": true,
169
+ "num_batches_to_accumulate": 8,
170
+ "max_policy_lag": 100000000,
171
+ "num_workers": 18,
172
+ "num_envs_per_worker": 8,
173
+ "batch_size": 1024,
174
+ "rollout": 128,
175
+ "recurrence": 1,
176
+ "normalize_returns": true,
177
+ "exploration_loss_coeff": 0.0,
178
+ "gae_lambda": 1.0,
179
+ "ppo_clip_value": 5.0,
180
+ "with_vtrace": false,
181
+ "max_grad_norm": 5.0,
182
+ "learning_rate": 0.0001,
183
+ "normalize_input": true,
184
+ "train_for_env_steps": 10000000000,
185
+ "save_milestones_sec": 10000,
186
+ "encoder_custom": "quad_multi_encoder",
187
+ "hidden_size": 256,
188
+ "nonlinearity": "tanh",
189
+ "policy_initialization": "xavier_uniform",
190
+ "actor_critic_share_weights": false,
191
+ "adaptive_stddev": false,
192
+ "use_rnn": false,
193
+ "with_wandb": true,
194
+ "wandb_tags": [
195
+ "multi"
196
+ ],
197
+ "quads_episode_duration": 15.0,
198
+ "quads_num_agents": 8,
199
+ "quads_neighbor_hidden_size": 256,
200
+ "quads_neighbor_encoder_type": "attention",
201
+ "quads_collision_reward": 5.0,
202
+ "quads_settle_reward": 0.0,
203
+ "quads_collision_hitbox_radius": 2.0,
204
+ "quads_collision_falloff_radius": 4.0,
205
+ "quads_collision_smooth_max_penalty": 10.0,
206
+ "neighbor_obs_type": "pos_vel",
207
+ "quads_use_numba": true,
208
+ "quads_local_obs": 6,
209
+ "quads_local_coeff": 1.0,
210
+ "quads_local_metric": "dist",
211
+ "quads_mode": "mix",
212
+ "quads_formation_size": 0.0,
213
+ "replay_buffer_sample_prob": 0.75,
214
+ "anneal_collision_steps": 300000000.0
215
+ },
216
+ "git_hash": "819afd374748be2bf5f9336ad8651ee215470c84",
217
+ "git_repo_name": "https://github.com/andrewzhang505/sample-factory.git",
218
+ "wandb_unique_id": "01_baseline_multi_drone_see_1111_20220816_115856_073413"
219
+ }