摘要
Abstract
Reinforcement learning can achieve autonomous learning in dynamic and complex environments,which makes it widely used in fields such as law,medicine,and finance.However,reinforcement learning still faces many problems such as the unobservable global state space,strong dependence on the reward function,and uncertain causality,which results in its weak interpretability,seriously affecting its promotion in related fields.It will encounter limitations such as difficulty in ju-dging whether the decision-making violates social legal and moral requirements,whether it is accurate and trustworthy,etc.In order to further understand the current status of interpretability research in reinforcement learning,this article discussed from the aspects of interpretable models,interpretable strategies,environment interaction and visualization,etc.Based on these,this article systematically discussed the research status of reinforcement learning interpretability,classified and explained its explainable methods,and finally proposed the future development direction of reinforcement learning interpretability.关键词
强化学习/可解释性/策略-值函数/环境交互/视觉解释Key words
reinforcement learning/interpretability/strategy-value functions/environment interaction/visual interpretation分类
信息技术与安全科学
