CAJ | 학술논문

车辆驻站是减少串车现象和改善公交服务可靠性的常用且有效控制策略，其执行过程需要在随机交互的系统环境中进行动态决策。考虑实时公交运营信息的可获得性，研究智能体完全合作环境下公交车辆驻站增强学习控制问题，建立基于多智能体系统的单线公交控制概念模型，描述学习框架下包括智能体状态、动作集、收益函数、协调机制等主要元素，采用hysteretic Q-learning算法求解问题。仿真实验结果表明该方法能有效防止串车现象并保持单线公交服务系统车头时距的均衡性。
차량주참시감소천차현상화개선공교복무가고성적상용차유효공제책략，기집행과정수요재수궤교호적계통배경중진행동태결책。고필실시공교운영신식적가획득성，연구지능체완전합작배경하공교차량주참증강학습공제문제，건립기우다지능체계통적단선공교공제개념모형，묘술학습광가하포괄지능체상태、동작집、수익함수、협조궤제등주요원소，채용hysteretic Q-learning산법구해문제。방진실험결과표명해방법능유효방지천차현상병보지단선공교복무계통차두시거적균형성。
Vehicle holding is a commonly used strategy among a variety of control strategies in transit operation for improv-ing transit service reliability, whose implementation needs dynamic decision-making in an interactive and stochastic sys-tem environment. This paper introduces a novel use of a reinforcement learning framework to obtain vehicle holding autonomous control strategy in cooperative multi-agent system. Transit operation control model is developed based on multi-agent system. In the multi-agent reinforcement learning framework, each bus is modeled as an independent agent with learning abilities, for which the state, actions and reward are defined and a coordination mechanism for multiple bus agents is designed to obtain a joint holding actions. The hysteretic Q-learning algorithm is used to solve this holding prob-lem. From the simulation experiments, the results illustrate that the proposed approach is able to prevent buses from bunching and regulate bus headway.