| resume: false |
| device: cuda |
| use_amp: false |
| seed: 0 |
| dataset_repo_id: iantc104/gaze_real_open_box_v1 |
| video_backend: pyav |
| training: |
| offline_steps: 15625 |
| num_workers: 8 |
| batch_size: 16 |
| eval_freq: -1 |
| log_freq: 100 |
| save_checkpoint: true |
| save_freq: 1000 |
| 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: 2.5e-05 |
| lr_backbone: 1.0e-05 |
| weight_decay: 0.0001 |
| grad_clip_norm: 10 |
| delta_timestamps: |
| action: |
| - 0.0 |
| - 0.030303030303030304 |
| - 0.06060606060606061 |
| - 0.09090909090909091 |
| - 0.12121212121212122 |
| - 0.15151515151515152 |
| - 0.18181818181818182 |
| - 0.21212121212121213 |
| - 0.24242424242424243 |
| - 0.2727272727272727 |
| - 0.30303030303030304 |
| - 0.3333333333333333 |
| - 0.36363636363636365 |
| - 0.3939393939393939 |
| - 0.42424242424242425 |
| - 0.45454545454545453 |
| - 0.48484848484848486 |
| - 0.5151515151515151 |
| - 0.5454545454545454 |
| - 0.5757575757575758 |
| - 0.6060606060606061 |
| - 0.6363636363636364 |
| - 0.6666666666666666 |
| - 0.696969696969697 |
| - 0.7272727272727273 |
| - 0.7575757575757576 |
| - 0.7878787878787878 |
| - 0.8181818181818182 |
| - 0.8484848484848485 |
| - 0.8787878787878788 |
| - 0.9090909090909091 |
| - 0.9393939393939394 |
| - 0.9696969696969697 |
| eval: |
| n_episodes: 1 |
| batch_size: 1 |
| use_async_envs: false |
| wandb: |
| enable: true |
| disable_artifact: true |
| project: av_aloha_real |
| notes: '' |
| fps: 33 |
| env: |
| name: real_world |
| task: null |
| state_dim: 21 |
| action_dim: 21 |
| fps: ${fps} |
| override_dataset_stats: |
| observation.images.overhead_cam: |
| mean: |
| - - - 0.485 |
| - - - 0.456 |
| - - - 0.406 |
| std: |
| - - - 0.229 |
| - - - 0.224 |
| - - - 0.225 |
| observation.images.worms_eye_cam: |
| mean: |
| - - - 0.485 |
| - - - 0.456 |
| - - - 0.406 |
| std: |
| - - - 0.229 |
| - - - 0.224 |
| - - - 0.225 |
| policy: |
| name: act |
| n_obs_steps: 1 |
| chunk_size: 33 |
| n_action_steps: 33 |
| input_shapes: |
| observation.images.overhead_cam: |
| - 3 |
| - 480 |
| - 640 |
| observation.images.worms_eye_cam: |
| - 3 |
| - 480 |
| - 640 |
| observation.state: |
| - ${env.state_dim} |
| output_shapes: |
| action: |
| - ${env.action_dim} |
| input_normalization_modes: |
| observation.images.overhead_cam: mean_std |
| observation.images.worms_eye_cam: mean_std |
| observation.state: mean_std |
| output_normalization_modes: |
| action: mean_std |
| image_size: |
| - 480 |
| - 640 |
| 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 |
|
|
