gh-NVlabs-Skill2Env
NVIDIA(保留所有權利)
Alibaba / Qwen Team
用集體技能強化代理(Skill2Env)
Reinforcing Agents with Collective Skills
Binfeng Xu, Jian Hu, Hao Zhang, Shaokun Zhang, Yifan Zhang, Michael Demoret, Jan Kautz, Yi Dong(NVID...
Agentic RLAgent SkillsSkill2Env終端代理DPPORubric Reward合成環境
Liang-Hsun Huang 許願