Hugging Face's logo

lerobot
/
act_aloha_sim_transfer_cube_human

Transformers
Safetensors
Inference Endpoints
Model card Files Community
1
act_aloha_sim_transfer_cube_human
File size: 2,834 Bytes 
5b65dc6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
device: cuda
seed: 1000
dataset_repo_id: lerobot/aloha_sim_transfer_cube_human
training:
  offline_steps: 100000
  online_steps: 0
  online_steps_between_rollouts: 1
  online_sampling_ratio: 0.5
  online_env_seed: ???
  eval_freq: 10000
  save_freq: 25000
  log_freq: 250
  save_model: true
  batch_size: 8
  lr: 1.0e-05
  lr_backbone: 1.0e-05
  weight_decay: 0.0001
  grad_clip_norm: 10
  override_dataset_stats:
    observation.images.top:
      mean:
      - - - 0.485
      - - - 0.456
      - - - 0.406
      std:
      - - - 0.229
      - - - 0.224
      - - - 0.225
  delta_timestamps:
    action:
    - 0.0
    - 0.02
    - 0.04
    - 0.06
    - 0.08
    - 0.1
    - 0.12
    - 0.14
    - 0.16
    - 0.18
    - 0.2
    - 0.22
    - 0.24
    - 0.26
    - 0.28
    - 0.3
    - 0.32
    - 0.34
    - 0.36
    - 0.38
    - 0.4
    - 0.42
    - 0.44
    - 0.46
    - 0.48
    - 0.5
    - 0.52
    - 0.54
    - 0.56
    - 0.58
    - 0.6
    - 0.62
    - 0.64
    - 0.66
    - 0.68
    - 0.7
    - 0.72
    - 0.74
    - 0.76
    - 0.78
    - 0.8
    - 0.82
    - 0.84
    - 0.86
    - 0.88
    - 0.9
    - 0.92
    - 0.94
    - 0.96
    - 0.98
    - 1.0
    - 1.02
    - 1.04
    - 1.06
    - 1.08
    - 1.1
    - 1.12
    - 1.14
    - 1.16
    - 1.18
    - 1.2
    - 1.22
    - 1.24
    - 1.26
    - 1.28
    - 1.3
    - 1.32
    - 1.34
    - 1.36
    - 1.38
    - 1.4
    - 1.42
    - 1.44
    - 1.46
    - 1.48
    - 1.5
    - 1.52
    - 1.54
    - 1.56
    - 1.58
    - 1.6
    - 1.62
    - 1.64
    - 1.66
    - 1.68
    - 1.7
    - 1.72
    - 1.74
    - 1.76
    - 1.78
    - 1.8
    - 1.82
    - 1.84
    - 1.86
    - 1.88
    - 1.9
    - 1.92
    - 1.94
    - 1.96
    - 1.98
eval:
  n_episodes: 50
  batch_size: 50
  use_async_envs: false
wandb:
  enable: true
  disable_artifact: false
  project: lerobot
  notes: ''
fps: 50
env:
  name: aloha
  task: AlohaTransferCube-v0
  from_pixels: true
  pixels_only: false
  image_size:
  - 3
  - 480
  - 640
  episode_length: 400
  fps: ${fps}
  state_dim: 14
  action_dim: 14
policy:
  name: act
  n_obs_steps: 1
  chunk_size: 100
  n_action_steps: 100
  input_shapes:
    observation.images.top:
    - 3
    - 480
    - 640
    observation.state:
    - ${env.state_dim}
  output_shapes:
    action:
    - ${env.action_dim}
  input_normalization_modes:
    observation.images.top: mean_std
    observation.state: mean_std
  output_normalization_modes:
    action: mean_std
  vision_backbone: resnet18
  pretrained_backbone_weights: ResNet18_Weights.IMAGENET1K_V1
  replace_final_stride_with_dilation: false
  pre_norm: false
  dim_model: 512
  n_heads: 8
  dim_feedforward: 3200
  feedforward_activation: relu
  n_encoder_layers: 4
  n_decoder_layers: 1
  use_vae: true
  latent_dim: 32
  n_vae_encoder_layers: 4
  use_temporal_aggregation: false
  dropout: 0.1
  kl_weight: 10.0