config.yaml

resume: false
device: cuda
use_amp: false
seed: 1000
dataset_repo_id: lerobot/pusht
video_backend: pyav
training:
  offline_steps: 100000
  num_workers: 4
  batch_size: 8
  eval_freq: 20000
  log_freq: 200
  save_checkpoint: true
  save_freq: 20000
  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
  lr: 1.0e-05
  lr_backbone: 1.0e-05
  weight_decay: 0.0001
  grad_clip_norm: 10
  delta_timestamps:
    action:
    - 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
    - 3.0
    - 3.1
    - 3.2
    - 3.3
    - 3.4
    - 3.5
    - 3.6
    - 3.7
    - 3.8
    - 3.9
    - 4.0
    - 4.1
    - 4.2
    - 4.3
    - 4.4
    - 4.5
    - 4.6
    - 4.7
    - 4.8
    - 4.9
    - 5.0
    - 5.1
    - 5.2
    - 5.3
    - 5.4
    - 5.5
    - 5.6
    - 5.7
    - 5.8
    - 5.9
    - 6.0
    - 6.1
    - 6.2
    - 6.3
    - 6.4
    - 6.5
    - 6.6
    - 6.7
    - 6.8
    - 6.9
    - 7.0
    - 7.1
    - 7.2
    - 7.3
    - 7.4
    - 7.5
    - 7.6
    - 7.7
    - 7.8
    - 7.9
    - 8.0
    - 8.1
    - 8.2
    - 8.3
    - 8.4
    - 8.5
    - 8.6
    - 8.7
    - 8.8
    - 8.9
    - 9.0
    - 9.1
    - 9.2
    - 9.3
    - 9.4
    - 9.5
    - 9.6
    - 9.7
    - 9.8
    - 9.9
eval:
  n_episodes: 50
  batch_size: 50
  use_async_envs: false
wandb:
  enable: true
  disable_artifact: false
  project: lerobot
  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: pixels_agent_pos
    render_mode: rgb_array
    visualization_width: 384
    visualization_height: 384
override_dataset_stats:
  observation.image:
    mean:
    - - - 0.5
    - - - 0.5
    - - - 0.5
    std:
    - - - 0.5
    - - - 0.5
    - - - 0.5
  observation.state:
    min:
    - 13.456424
    - 32.938293
    max:
    - 496.14618
    - 510.9579
  action:
    min:
    - 12.0
    - 25.0
    max:
    - 511.0
    - 511.0
policy:
  name: act
  n_obs_steps: 1
  chunk_size: 100
  n_action_steps: 100
  input_shapes:
    observation.image:
    - 3
    - 96
    - 96
    observation.state:
    - ${env.state_dim}
  output_shapes:
    action:
    - ${env.action_dim}
  input_normalization_modes:
    observation.image: 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
  temporal_ensemble_coeff: null
  dropout: 0.1
  kl_weight: 10.0