Hugging Face's logo

andrewzhang505
/
quad-swarm-rl-sf2

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Model card Files Metrics Community
1
quad-swarm-rl-sf2
File size: 7,127 Bytes 
922f838
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
190
191
192
193
194
195
 
{
  "help": false,
  "algo": "APPO",
  "env": "quadrotor_multi",
  "experiment": "00_baseline_see_0",
  "train_dir": "./train_dir/quad_single_baseline/baseline_",
  "restart_behavior": "resume",
  "device": "gpu",
  "seed": 0,
  "num_policies": 1,
  "async_rl": true,
  "serial_mode": false,
  "batched_sampling": false,
  "num_batches_to_accumulate": 2,
  "worker_num_splits": 2,
  "policy_workers_per_policy": 1,
  "max_policy_lag": 100000000,
  "num_workers": 36,
  "num_envs_per_worker": 4,
  "batch_size": 1024,
  "num_batches_per_epoch": 1,
  "num_epochs": 1,
  "rollout": 128,
  "recurrence": 1,
  "shuffle_minibatches": true,
  "gamma": 0.99,
  "reward_scale": 1.0,
  "reward_clip": 1000.0,
  "value_bootstrap": false,
  "normalize_returns": false,
  "exploration_loss_coeff": 0.0,
  "value_loss_coeff": 0.5,
  "kl_loss_coeff": 0.0,
  "exploration_loss": "entropy",
  "gae_lambda": 1.0,
  "ppo_clip_ratio": 0.1,
  "ppo_clip_value": 5.0,
  "with_vtrace": false,
  "vtrace_rho": 1.0,
  "vtrace_c": 1.0,
  "optimizer": "adam",
  "adam_eps": 1e-06,
  "adam_beta1": 0.9,
  "adam_beta2": 0.999,
  "max_grad_norm": 5.0,
  "learning_rate": 0.0001,
  "lr_schedule": "constant",
  "lr_schedule_kl_threshold": 0.008,
  "obs_subtract_mean": 0.0,
  "obs_scale": 1.0,
  "normalize_input": false,
  "decorrelate_experience_max_seconds": 10,
  "decorrelate_envs_on_one_worker": true,
  "actor_worker_gpus": [],
  "set_workers_cpu_affinity": true,
  "force_envs_single_thread": true,
  "default_niceness": 0,
  "experiment_summaries_interval": 60,
  "stats_avg": 100,
  "train_for_env_steps": 10000000000,
  "train_for_seconds": 10000000000,
  "save_every_sec": 120,
  "keep_checkpoints": 3,
  "load_checkpoint_kind": "latest",
  "save_milestones_sec": 10000,
  "save_best_every_sec": 5,
  "save_best_metric": "reward",
  "save_best_after": 100000,
  "benchmark": false,
  "encoder_type": "mlp",
  "encoder_subtype": "mlp_quads",
  "encoder_custom": "quad_multi_encoder",
  "encoder_extra_fc_layers": 0,
  "hidden_size": 16,
  "nonlinearity": "tanh",
  "policy_initialization": "xavier_uniform",
  "policy_init_gain": 1.0,
  "actor_critic_share_weights": false,
  "adaptive_stddev": false,
  "initial_stddev": 1.0,
  "use_rnn": false,
  "rnn_type": "gru",
  "rnn_num_layers": 1,
  "env_gpu_actions": false,
  "env_frameskip": 1,
  "env_framestack": 4,
  "pixel_format": "CHW",
  "with_wandb": true,
  "wandb_user": null,
  "wandb_project": "sample_factory",
  "wandb_group": null,
  "wandb_job_type": "SF",
  "wandb_tags": [
    "sf2"
  ],
  "quads_discretize_actions": -1,
  "quads_clip_input": false,
  "quads_effort_reward": null,
  "quads_episode_duration": 15.0,
  "quads_num_agents": 1,
  "quads_neighbor_hidden_size": 256,
  "quads_neighbor_encoder_type": "no_encoder",
  "quads_collision_reward": 5.0,
  "quads_collision_obstacle_reward": 0.0,
  "quads_settle_reward": 0.0,
  "quads_settle": false,
  "quads_vel_reward_out_range": 0.8,
  "quads_settle_range_meters": 1.0,
  "quads_collision_hitbox_radius": 2.0,
  "quads_collision_falloff_radius": 4.0,
  "quads_collision_smooth_max_penalty": 10.0,
  "neighbor_obs_type": "none",
  "quads_use_numba": true,
  "quads_obstacle_mode": "no_obstacles",
  "quads_obstacle_num": 0,
  "quads_obstacle_type": "sphere",
  "quads_obstacle_size": 0.0,
  "quads_obstacle_traj": "gravity",
  "quads_local_obs": -1,
  "quads_local_coeff": 1.0,
  "quads_local_metric": "dist",
  "quads_view_mode": "local",
  "quads_adaptive_env": false,
  "quads_mode": "mix",
  "quads_formation": "circle_horizontal",
  "quads_formation_size": 0.0,
  "room_dims": [
    10,
    10,
    10
  ],
  "quads_obs_repr": "xyz_vxyz_R_omega",
  "replay_buffer_sample_prob": 0.0,
  "anneal_collision_steps": 0.0,
  "quads_obstacle_obs_mode": "relative",
  "quads_obstacle_hidden_size": 32,
  "quads_collision_obst_smooth_max_penalty": 10.0,
  "quads_obst_penalty_fall_off": 10.0,
  "use_spectral_norm": false,
  "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 --hidden_size=16 --neighbor_obs_type=none --quads_local_obs=-1 --quads_num_agents=1 --replay_buffer_sample_prob=0.0 --anneal_collision_steps=0 --save_milestones_sec=10000 --quads_neighbor_encoder_type=no_encoder --serial_mode=False --with_wandb=True --wandb_tags sf2 --seed=0 --experiment=00_baseline_see_0 --train_dir=./train_dir/quad_single_baseline/baseline_",
  "cli_args": {
    "algo": "APPO",
    "env": "quadrotor_multi",
    "experiment": "00_baseline_see_0",
    "train_dir": "./train_dir/quad_single_baseline/baseline_",
    "seed": 0,
    "serial_mode": false,
    "max_policy_lag": 100000000,
    "num_workers": 36,
    "num_envs_per_worker": 4,
    "batch_size": 1024,
    "rollout": 128,
    "recurrence": 1,
    "exploration_loss_coeff": 0.0,
    "gae_lambda": 1.0,
    "ppo_clip_value": 5.0,
    "with_vtrace": false,
    "max_grad_norm": 5.0,
    "learning_rate": 0.0001,
    "train_for_env_steps": 10000000000,
    "save_milestones_sec": 10000,
    "encoder_custom": "quad_multi_encoder",
    "hidden_size": 16,
    "nonlinearity": "tanh",
    "policy_initialization": "xavier_uniform",
    "actor_critic_share_weights": false,
    "adaptive_stddev": false,
    "use_rnn": false,
    "with_wandb": true,
    "wandb_tags": [
      "sf2"
    ],
    "quads_episode_duration": 15.0,
    "quads_num_agents": 1,
    "quads_neighbor_hidden_size": 256,
    "quads_neighbor_encoder_type": "no_encoder",
    "quads_collision_reward": 5.0,
    "quads_settle_reward": 0.0,
    "quads_collision_hitbox_radius": 2.0,
    "quads_collision_falloff_radius": 4.0,
    "quads_collision_smooth_max_penalty": 10.0,
    "neighbor_obs_type": "none",
    "quads_use_numba": true,
    "quads_local_obs": -1,
    "quads_local_coeff": 1.0,
    "quads_local_metric": "dist",
    "quads_mode": "mix",
    "quads_formation_size": 0.0,
    "replay_buffer_sample_prob": 0.0,
    "anneal_collision_steps": 0.0
  },
  "git_hash": "e6745398a0413737776f3cd1681cf77173b05921",
  "git_repo_name": "https://github.com/andrewzhang505/sample-factory.git",
  "wandb_unique_id": "00_baseline_see_0_20220712_191712_050475"
}