菜单
Run GapONet training. Use when the user invokes /gaponet-train or $gaponet-train, or asks to train a GapONet humanoid policy after data preparation using Isaac Lab, Isaac Sim, rsl_rl, DeepONet, Transformer, MLP, or the unified runner.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
GapONet sim-to-real humanoid robot control workflows for Isaac Lab. Use when working on the GapONet repository or tasks involving GapONet setup, environment validation, training, evaluation, checkpoint export, lightweight deployment, DeepONet, Transformer or MLP policy configs, humanoid operator or AMASS tasks, motion data schemas, robot asset integration, or agent-friendly run artifacts.
Run GapONet data preparation. Use when the user invokes /gaponet-data or $gaponet-data, or asks to process, validate, stage, copy, symlink, or prepare GapONet motion .npz data for training or inference.
Run GapONet inference and evaluation. Use when the user invokes /gaponet-inf or $gaponet-inf, or asks to export a GapONet checkpoint to TorchScript/JIT, run lightweight inference, deploy a policy, evaluate test motion data, or produce inference metrics.
基于 SOC 职业分类
| name | gaponet-train |
| description | Run GapONet training. Use when the user invokes /gaponet-train or $gaponet-train, or asks to train a GapONet humanoid policy after data preparation using Isaac Lab, Isaac Sim, rsl_rl, DeepONet, Transformer, MLP, or the unified runner. |
Run the training stage from the GapONet repository root, identified by scripts/run_gaponet_job.py, check_env.py, and configs/train_default.json.
source/sim2real/sim2real/tasks/humanoid_operator/motions/motion_amass/edited_27dof/test.npz is missing, run $gaponet-data or ask for an input .npz.python check_env.py --output-json ./runs/train/env_check_result.json
python scripts/run_gaponet_job.py --mode train --config configs/train_default.json --output-dir ./runs/train
max_iterations, num_envs, run_name, device, or task, create a run-local JSON config under runs/train/ by copying configs/train_default.json, apply the overrides, and pass that config to the wrapper.configs/train_default.jsonIsaac-Humanoid-Operator-Delta-Actionsource/sim2real/sim2real/tasks/humanoid_operator/motions/motion_amass/edited_27dof/test.npzruns/trainrun_manifest.json, training_metrics.json, stdout.log, stderr.logConsider training complete only when runs/train/run_manifest.json reports "status": "success" or when a clear blocking failure is reported. Training can be long and Isaac Sim dependent; do not fake completion from command launch alone.