Inverse Reinforcement Learning without an Optimal Demonstrator: A Feasible Reward Set Approach 文章

ArXiv CS.AI2026-06-01NEWSen作者: Kihyun Kim, Shripad Deshmukh, Nikos Vlassis, Jiawei Zhang
查看原文 →
关系图谱

Inverse Reinforcement Learning without an Optimal Demonstrator: A Feasible Reward Set Approach · 相关技术

相关技术

reinforcement learning