ASK in the Dark: Uncertainty-Gated LLM Assistance under Partial Observability
黑暗中的询问:部分可观测性下的不确定性门控语言模型辅助
机构 * Kunumi Institute(库努米研究所) ; King’s College London(伦敦国王学院)
AI总结 研究部分可观测性下强化学习智能体,指出普通不确定性门控方法失败原因是上下文问题。提出ASK+,为语言模型提供轨迹感知上下文和结构化推理,证明预测熵信号可行,在多环境中取得更好效果,强调提示设计重要性。
Comments Accepted at the IJCAI-ECAI Joint Workshop on Planning for Complex Real-World Applications and Bridging the Gap Between AI Planning and (Reinforcement) Learning