基于Agent的递阶强化学习模型与体系结构

通过引入频率最大Q值启发式学习算法,对一种递阶强化学习方法进行改进,解决在庞大状态空间和动态变化环境中对Agent进行最优行为策略学习的问题。引入属性维护算子以及承诺和规划意识属性,对经典信念、愿望、意图模型进行扩展,给出意识属性的理性维护过程,增强Agent的自适应性并使Agent具有在动态环境中进行在线学习的能力。根据意识模型提出一种具有主动性、适应性、反应性、社会性的Agent体系结构,并根据该体系结构开发出一种路径规划Agent。通过对行驶环境的组态设定,模拟车辆复杂的行驶状态,并通过对行驶状态的不断学习,最终获得最优路径,证明体系结构的可行性和有效性。

Model and Architecture of Hierarchical Reinforcement Learning Based on Agent

By introducing frequency maximum Q heuristic learning algorithm,a hierarchical reinforcement learning method is improved,this method solves the problem of agent optimal strategy learning in a large scale state space and dynamic changing environment. Bringing attribute maintenance operator,the attribute of promise and layout into the classical belief,desire,intention(BDI) model,which is modified to increase the adaptability and in-line learning ability of agent,the rational maintenance process of consciousne...