arXiv Artificial Intelligence· Tong Nie, Yuewen Mei, Junlin He, Yihong Tang, Jian Sun, Wei Ma·· 2 天前AI 评分31
世界模型作为对手：面向鲁棒运动规划的多智能体自博弈微调
World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning
AI 导读
研究提出 Adversarial World Modeling（AWM）多智能体自博弈微调框架，将对抗鲁棒规划学习建模为约束 min-max 博弈，并用解耦求解器分别处理内层最小化与外层最大化。
来源：arXiv Artificial Intelligence · arxiv.org