arXiv：cs.LG· T. Y. Tsui, Zihao Ye, Pengxiang Cai, Yanchao Li, Yuqiang Li, Zhehong Ai·· 4 小时前AI 评分35
Minimal-Witness Reinforcement Learning：从验证器反馈中学习最小充分见证
Minimal Witness Reinforcement Learning
AI 导读
研究者提出 Minimal-Witness Reinforcement Learning（MWRL），把“找出充分产生结果的最小条件”形式化为最小见证识别问题。
正文
Abstract:``What are the irreducible conditions that are sufficient to produce an outcome?'' is one of the most common questions that recur across computation and science. Its answers, the minimal sufficient witnesses, are what we mean by explanations, mechanisms and reasons. These problems usually ask for multiple minimal witnesses, yet standard RL methods may reveal only one solution or redundant ones. We formalize this problem as minimal-witness identification and introduce Minimal-Witness Reinforcement Learning (MWRL). MWRL takes the union of the sets certified by successful proposals sampled from the policy and credits each proposal for the coverage the group union would lose without that proposal. This credit assignment, derived directly from the problem definition, unifies the demands for minimality and recovery of alternatives from a single black-box verifier bit. Under this principle, we derive a value iteration planner that recovers the entire family of witnesses and a policy gradient method that can scale to large language models. Across different experimental settings, MWRL recovers most minimal witnesses, while other methods return redundant supersets or a single witness. By making witness families learnable from verifier feedback, MWRL expands the scope of reinforcement learning beyond single-solution optimization. Our code is available at this https URL.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Logic in Computer Science (cs.LO) |
| Cite as: | arXiv:2610.07226 [cs.LG] |
| (or arXiv:2610.07226v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07226 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: T. Y. Tsui [view email]
[v1]
Mon, 5 Oct 2026 18:34:49 UTC (746 KB)
来源：arXiv：cs.LG · arxiv.org