★ 80 +12 ⑂ 2 Python MIT 75
waltstephen/CaPtain
CaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents — CaPtain-Harness, SFT and RL training code, benchmark adapters
创建于 2026-09-16 · 最近推送 2026-11-03 · 首次出现在推荐 2026-11-03
code-as-policyembodied-ailiberollm-agentrobot-learningroboticsvision-language-model robotembodied
兴趣：vision-language-action (VLA) models and foundation models for robots