一种高斯过程的带参近似策略迭代算法  

Parametric Approximation Policy Iteration Algorithm Based on Gaussian Process

作　　者：傅启明[1] 刘全[1,2] 伏玉琛[1] 周谊成[1] 于俊[1] 

机构地区：[1]苏州大学计算机科学与技术学院,江苏苏州215006 [2]符号计算与知识工程教育部重点实验室(吉林大学),吉林长春130012

出　　处：《软件学报》2013年第11期2676-2686,共11页Journal of Software

基　　金：国家自然科学基金(61070223;61103045;61170020;61272005;61272244);江苏省自然科学基金(BK2012616);吉林大学符号计算与知识工程教育部重点实验室基金(93K172012K04)

摘　　要：在大规模状态空间或者连续状态空间中,将函数近似与强化学习相结合是当前机器学习领域的一个研究热点;同时,在学习过程中如何平衡探索和利用的问题更是强化学习领域的一个研究难点.针对大规模状态空间或者连续状态空间、确定环境问题中的探索和利用的平衡问题,提出了一种基于高斯过程的近似策略迭代算法.该算法利用高斯过程对带参值函数进行建模,结合生成模型,根据贝叶斯推理,求解值函数的后验分布.在学习过程中,根据值函数的概率分布,求解动作的信息价值增益,结合值函数的期望值,选择相应的动作.在一定程度上,该算法可以解决探索和利用的平衡问题,加快算法收敛.将该算法用于经典的Mountain Car问题,实验结果表明,该算法收敛速度较快,收敛精度较好.In machine learning with large or continuous state space, it is a hot topic to combine the function approximation and reinforcement learning. The study also faces a very difficult problem of how to balance the exploration and exploitation in reinforcement learning. In allusion to the exploration and exploitation dilemma in the large or continuous state space, this paper presents a novel policy iteration algorithm based on Gaussian process in deterministic environment. The algorithm uses Gaussian process to model the action-value function, and in conjunction with generative model, obtains the posteriori distribution of the parameter vector of the action-value function by Bayesian inference. During the learning process, it computes the value of perfect information according to the posteriori distribution, and then selects the appropriate action with respect to the expected value of the action-value function. The algorithm achieves the balance between exploration and exploitation to certain extent, and therefore accelerates the convergence. The experimental results on the Mountain Car problem show that the algorithm has faster convergence rate and better convergence performance.

关 键 词：强化学习 策略迭代 高斯过程 贝叶斯推理 函数近似 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]