Evaluating XAI Support From A Hierarchical Reinforcement Learning Policy in Human-Agent Collaboration
评估人机协作中分层强化学习策略的可解释人工智能(XAI)支持
专题命中 规划决策 :agent(title,abstract);分类 cs.AI;autonomous agent(journal_ref)
AI总结 本文首次在Overcooked-AI基准中,对分层特设智能体(HA²)架构生成的文本/音频实时解释开展被试间实验,分析XAI对人机协作的影响,为评估可解释强化学习架构建立基线方法。
Comments 13 pages, 6 figures, accepted as an Extended Abstract at AAMAS 2026
Journal ref Proc. of the 25th International Conference on Autonomous Agents and Multiagent Systems. 2026. p. 3259-3261