Solution to reinforcement learning problems with artificial potential field

来源期刊：中南大学学报(英文版)2008年第4期

论文作者：谢丽娟 谢光荣 陈焕文 李小俚

文章页码：552 - 557

Key words：reinforcement learning; path planning; mobile robot navigation; artificial potential field; virtual water-flow

Abstract: A novel method was designed to solve reinforcement learning problems with artificial potential field. Firstly a reinforcement learning problem was transferred to a path planning problem by using artificial potential field(APF), which was a very appropriate method to model a reinforcement learning problem. Secondly, a new APF algorithm was proposed to overcome the local minimum problem in the potential field methods with a virtual water-flow concept. The performance of this new method was tested by a gridworld problem named as key and door maze. The experimental results show that within 45 trials, good and deterministic policies are found in almost all simulations. In comparison with WIERING’s HQ-learning system which needs 20 000 trials for stable solution, the proposed new method can obtain optimal and stable policy far more quickly than HQ-learning. Therefore, the new method is simple and effective to give an optimal solution to the reinforcement learning problem.

基金信息：the National Natural Science Foundation of China