| { |
| "action": { |
| "dimension": 14, |
| "execute_horizon": 10, |
| "horizon": 32, |
| "padding": "end_of_episode_clamp_to_last_frame_supervised", |
| "representation": "14-D absolute joint/qpos" |
| }, |
| "benchmark": "robodojo", |
| "data": { |
| "camera_keys": { |
| "head": "observation.images.cam_high", |
| "left_wrist": "observation.images.cam_left_wrist", |
| "right_wrist": "observation.images.cam_right_wrist" |
| }, |
| "camera_order": [ |
| "head", |
| "left_wrist", |
| "right_wrist" |
| ], |
| "codec": { |
| "decode_clip": false, |
| "encode_clamp_sigma": 12.0, |
| "grippers": "2x-1", |
| "joints": "zscore_mean_std_all_clean_frames", |
| "statistics": "codec_statistics.json", |
| "version": "reswam-robodojo-absolute-qpos-zscore-joints-affine-grippers-14d-v1" |
| }, |
| "metadata_frequency_hz": 25, |
| "preprocess_to_256": "direct_bicubic_antialias_no_crop", |
| "vlm_camera_order": [ |
| "head", |
| "left_wrist", |
| "right_wrist" |
| ] |
| }, |
| "dataset": { |
| "action_dimension": 14, |
| "action_representation": "14-D absolute joint/qpos", |
| "camera_order": [ |
| "head", |
| "left_wrist", |
| "right_wrist" |
| ], |
| "cleaning_variant": "all-frames", |
| "control_hz": 25, |
| "episodes": 3500, |
| "frames": 1856102, |
| "gripper_semantics": "larger_is_more_open", |
| "hf_repo": "RoboDojo-Benchmark/RoboDojo", |
| "joint_order": [ |
| "left_joint_0", |
| "left_joint_1", |
| "left_joint_2", |
| "left_joint_3", |
| "left_joint_4", |
| "left_joint_5", |
| "left_joint_6", |
| "right_joint_0", |
| "right_joint_1", |
| "right_joint_2", |
| "right_joint_3", |
| "right_joint_4", |
| "right_joint_5", |
| "right_joint_6" |
| ], |
| "sampler": "uniform_concat_every_clean_frame_end_clamped_supervised", |
| "state_dimension": 14, |
| "state_representation": "14-D current qpos", |
| "tasks": 35 |
| }, |
| "evaluation": { |
| "action_type": "joint", |
| "benchmark": "RoboDojo sim (Isaac Sim 5.1 / Isaac Lab 2.3), official XPolicyLab websocket client", |
| "control_hz": 25, |
| "env_cfg": "arx_x5", |
| "execute_horizon": 10, |
| "num_configs": 54, |
| "num_tasks": 42, |
| "prediction_horizon": 32, |
| "seeds": [ |
| 0 |
| ], |
| "total_episodes": 2100 |
| }, |
| "flow": { |
| "action_noise": "independent_gaussian", |
| "action_scheduler_shift": 1, |
| "action_tau": "independent_uniform_shifted", |
| "inference_rounds": 10, |
| "synchronous_commit": true, |
| "world_noise": "independent_gaussian", |
| "world_scheduler_shift": 5, |
| "world_tau": "independent_uniform_shifted" |
| }, |
| "model": { |
| "dino": { |
| "architecture": "DINOv3-B/16", |
| "combine": "arithmetic_mean", |
| "frozen": true, |
| "model_id": "facebook/dinov3-vitb16-pretrain-lvd1689m", |
| "remove_prefix_tokens": true, |
| "selected_blocks": [ |
| 8, |
| 10 |
| ], |
| "spatial_pooling": "2x2", |
| "target_token_ln": true, |
| "tokens": 64 |
| }, |
| "expert": { |
| "depth": 12, |
| "expert_parameter_count": 493608462, |
| "ffn_dim": 4096, |
| "heads": 16, |
| "hidden_dim": 1024, |
| "state_dropout_prob": 0.0, |
| "use_state_null_tokens": false |
| }, |
| "rynnbrain": { |
| "backbone_parameter_count": 1755487104, |
| "repo": "Alibaba-DAMO-Academy/RynnBrain1.1-2B", |
| "text_hidden_size": 2048, |
| "text_layers": 16, |
| "vision_layers": 24 |
| } |
| }, |
| "optimizer": { |
| "betas": [ |
| 0.9, |
| 0.95 |
| ], |
| "clip_grad_norm": 1.0, |
| "expert_min_lr": 1e-05, |
| "expert_peak_lr": 0.0001, |
| "name": "AdamW", |
| "precision": "bfloat16", |
| "vlm_min_lr": 1e-06, |
| "vlm_peak_lr": 1e-05, |
| "weight_decay": 1e-08 |
| }, |
| "schema_version": "reswam-robodojo-config-v1", |
| "training": { |
| "fsdp": "FULL_SHARD", |
| "global_batch": 256, |
| "gradient_accumulation": 2, |
| "microbatch": 32, |
| "seed": 20260907, |
| "world_size": 4 |
| }, |
| "world": { |
| "camera": "head", |
| "loss_weight": 0.1, |
| "objective": "endpoint_only_extra_LN_delta", |
| "target_offset": 32 |
| } |
| } |
|
|
