arXiv:2608.21372cs.AIcs.LG2026-08

AI通过试错学习隐藏规则,探索推理与迁移能力。

AI Learning and Conceptual Transfer in the Game of Hidden Rules

论文配图:AI Learning and Conceptual Transfer in the Game of Hidden Rules
图 1 · 摘自论文原文
  • 用Transformer-A2C框架让智能体从反馈中推断隐藏规则。
  • 对象中心表征比特征中心更利于规则识别与泛化。
  • 适合研究强化学习、规则推理及人机协作的学习机制。

本报告总结了在隐规则游戏(Game of Hidden Rules, GOHR)中的研究工作,重点包括基于强化学习的智能体通过试错反馈推断隐藏规则、表征设计、规则难度分析、迁移学习、泛化能力以及伪机器人辅助的人类学习行为分析。研究采用基于Transformer的A2C框架,对比了特征中心与对象中心的表征方法,实验揭示了不同表征对规则学习效率的影响,并对人类学习数据进行了分类分析,为理解智能体与人类在复杂规则环境下的认知机制提供了依据。

原文摘要 · Abstract (English)

This report summarizes the work conducted on the Game of Hidden Rules (GOHR), focusing on reinforcement learning agents trained to infer hidden rules from trial-and-error feedback, representation design, rule difficulty analysis, transfer learning, generalization, and pseudo-bot-assisted human learning analysis. The report focuses on the Transformer-based A2C framework, Feature-Centric and Object-Centric representations, experimental findings, and classification of human learning data.

强化学习规则推理迁移学习

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。