[2605.30903] Inverse Reinforcement Learning without an Optimal Demonstrator: A Feasible Reward Set Approach
![[2605.30903] Inverse Reinforcement Learning without an Optimal Demonstrator: A Feasible Reward Set Approach](/static/img/curated/afbytes-us.png)
AI disclosure
Summary
Abstract page for arXiv paper 2605.30903: Inverse Reinforcement Learning without an Optimal Demonstrator: A Feasible Reward Set Approach