Decomposition Based Multi-Objective Evolutionary Algorithm in XCS for Multi-Objective Reinforcement Learning
2018 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC)(2018)
摘要
Learning Classifier Systems (LCSs) have been widely used to tackle Reinforcement Learning (RL) problems as they have a good generalization ability and provide a simple understandable rule-based solution. The accuracy-based LCS, XCS, has been most popularly used for single-objective RL problems. As many real-world problems exhibit multiple conflicting objectives recent work has sought to adapt XCS to Multi-Objective Reinforcement Learning (MORL) tasks. However, many of these algorithms need large storage or cannot discover the Pareto Optimal solutions. This is due to the complexity of finding a policy having multiple steps to multiple possible objectives. This paper aims to employ a decomposition strategy based on MOEA/D in XCS to approximate complex Pareto Fronts. In order to achieve multi-objective learning, a new MORL algorithm has been developed based on XCS and MOEA/D. The experimental results show that on complex bi-objective maze problems our MORL algorithm is able to learn a group of Pareto optimal solutions for MORL problems without huge storage. Analysis of the learned policies shows successful trade-offs between the distance to the reward versus the amount of reward itself.
更多查看译文
关键词
XCS,accuracy-based LCS,Pareto Optimal solutions,complex bi-objective maze problems,Multi-Objective Evolutionary Algorithm,Learning Classifier Systems,rule-based solution,Multi-Objective Reinforcement Learning,MORL,MORL tasks,complex Pareto Fronts
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络