1
Against Proxy Optimization
直指AI优化核心痛点：追求代理目标可能让系统偏离真实意图，一篇值得从业者深读的批判性视角论文
arXiv:2606.23597v1 Announce Type: new Abstract: I discuss conditions under which maximizing a proxy utility function is harmful and suggest this poses…
2
Target-Aligned Bellman Backup for Cross-domain Offline Reinforcement Learning
跨领域离线强化学习新方法，用对齐贝尔曼备份解决域间转移难题。
arXiv:2605.22376v1 Announce Type: new Abstract: Cross-domain offline reinforcement learning (CDRL) aims to improve policy learning in a target domain …