Hugging Face's logo

jadechoghari
/
dot_pusht_keypoints_best

Robotics
Safetensors
lerobot
model_hub_mixin
pytorch_model_hub_mixin
dot
Model card Files Community
dot_pusht_keypoints_best
File size: 3,535 Bytes 
014f19a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
 
resume: false
device: cuda
use_amp: true
seed: 100000
dataset_repo_id: lerobot/pusht_keypoints
video_backend: pyav
training:
  offline_steps: 1000000
  num_workers: 24
  batch_size: 24
  eval_freq: 10000
  log_freq: 1000
  save_checkpoint: true
  save_freq: 50000
  online_steps: 0
  online_rollout_n_episodes: 1
  online_rollout_batch_size: 1
  online_steps_between_rollouts: 1
  online_sampling_ratio: 0.5
  online_env_seed: null
  online_buffer_capacity: null
  online_buffer_seed_size: 0
  do_online_rollout_async: false
  image_transforms:
    enable: false
    max_num_transforms: 3
    random_order: false
    brightness:
      weight: 1
      min_max:
      - 0.8
      - 1.2
    contrast:
      weight: 1
      min_max:
      - 0.8
      - 1.2
    saturation:
      weight: 1
      min_max:
      - 0.5
      - 1.5
    hue:
      weight: 1
      min_max:
      - -0.05
      - 0.05
    sharpness:
      weight: 1
      min_max:
      - 0.8
      - 1.2
  save_model: true
  grad_clip_norm: 50
  lr: 0.0001
  min_lr: 0.0001
  lr_cycle_steps: 300000
  weight_decay: 1.0e-05
  delta_timestamps:
    observation.environment_state:
    - -1.5
    - -1.4
    - -1.3
    - -1.2
    - -1.1
    - -1.0
    - -0.9
    - -0.8
    - -0.7
    - -0.6
    - -0.5
    - -0.1
    - 0.0
    observation.state:
    - -1.5
    - -1.4
    - -1.3
    - -1.2
    - -1.1
    - -1.0
    - -0.9
    - -0.8
    - -0.7
    - -0.6
    - -0.5
    - -0.1
    - 0.0
    action:
    - -1.5
    - -1.4
    - -1.3
    - -1.2
    - -1.1
    - -1.0
    - -0.9
    - -0.8
    - -0.7
    - -0.6
    - -0.5
    - -0.1
    - 0.0
    - 0.1
    - 0.2
    - 0.3
    - 0.4
    - 0.5
    - 0.6
    - 0.7
    - 0.8
    - 0.9
    - 1.0
    - 1.1
    - 1.2
    - 1.3
    - 1.4
    - 1.5
    - 1.6
    - 1.7
    - 1.8
    - 1.9
    - 2.0
    - 2.1
    - 2.2
    - 2.3
    - 2.4
    - 2.5
    - 2.6
    - 2.7
    - 2.8
    - 2.9
eval:
  n_episodes: 100
  batch_size: 100
  use_async_envs: false
wandb:
  enable: true
  disable_artifact: false
  project: pusht
  notes: ''
fps: 10
env:
  name: pusht
  task: PushT-v0
  image_size: 96
  state_dim: 2
  action_dim: 2
  fps: ${fps}
  episode_length: 300
  gym:
    obs_type: environment_state_agent_pos
    render_mode: rgb_array
    visualization_width: 384
    visualization_height: 384
override_dataset_stats:
  observation.environment_state:
    min:
    - 0.0
    - 0.0
    - 0.0
    - 0.0
    - 0.0
    - 0.0
    - 0.0
    - 0.0
    - 0.0
    - 0.0
    - 0.0
    - 0.0
    - 0.0
    - 0.0
    - 0.0
    - 0.0
    max:
    - 512.0
    - 512.0
    - 512.0
    - 512.0
    - 512.0
    - 512.0
    - 512.0
    - 512.0
    - 512.0
    - 512.0
    - 512.0
    - 512.0
    - 512.0
    - 512.0
    - 512.0
    - 512.0
  observation.state:
    min:
    - 0.0
    - 0.0
    max:
    - 512.0
    - 512.0
  action:
    min:
    - 0.0
    - 0.0
    max:
    - 512.0
    - 512.0
policy:
  name: dot
  n_obs_steps: 3
  train_horizon: 30
  inference_horizon: 30
  lookback_obs_steps: 10
  lookback_aug: 5
  input_shapes:
    observation.environment_state:
    - 16
    observation.state:
    - ${env.state_dim}
  output_shapes:
    action:
    - ${env.action_dim}
  input_normalization_modes:
    observation.environment_state: min_max
    observation.state: min_max
  output_normalization_modes:
    action: min_max
  state_noise: 0.01
  noise_decay: 0.999995
  pre_norm: true
  dim_model: 128
  n_heads: 8
  dim_feedforward: 512
  n_decoder_layers: 8
  dropout: 0.1
  alpha: 0.75
  train_alpha: 0.9
  predict_every_n: 1
  return_every_n: 2