隐规则博弈中的人工智能学习与概念迁移
AI Learning and Conceptual Transfer in the Game of Hidden Rules
浏览论文内容
中文总结 AI 辅助
本研究围绕隐规则博弈(GOHR),采用基于Transformer的A2C框架,开展强化学习智能体的规则推断、表征设计等研究,为相关领域提供实验依据。
中文摘要 AI 辅助
本报告总结了针对隐规则博弈(GOHR)开展的研究工作,聚焦于训练强化学习智能体从试错反馈中推断隐规则,涉及表征设计、规则难度分析、迁移学习、泛化性及伪机器人辅助人类学习分析等内容。研究重点为基于Transformer的A2C框架、以特征为中心和以对象为中心的表征,以及实验结果与人类学习数据分类。
英文摘要
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.
发表机构
- Rutgers University(罗格斯大学)
- University of Southern California(南加州大学)
机构由 AI 辅助整理,请以论文原文为准。