Abstract
Obtaining the accurate value estimation and reducing the estimation bias are the key issues in reinforcement learning.However,current methods that address the overestimation prob-lem tend to introduce underestimation,which face a challenge of precise decision-making in many fields.To address this issue,we conduct a theoretical analysis of the underestimation bias and pro-pose the minmax operation,which allow for flexible control of the estimation bias.Specifically,we select the maximum value of each action from multiple parallel state-action networks to create a new state-action value sequence.Then,a minimum value is selected to obtain more accurate value estimations.Moreover,based on the minmax operation,we propose two novel algorithms by com-bining Deep Q-Network(DQN)and Double DQN(DDQN),named minmax-DQN and minmax-DDQN.Meanwhile,we conduct theoretical analyses of the estimation bias and variance caused by our proposed minmax operation,which show that this operation significantly improves both under-estimation and overestimation biases and leads to the unbiased estimation.Furthermore,the vari-ance is also reduced,which is helpful to improve the network training stability.Finally,we conduct numerous comparative experiments in various environments,which empirically demonstrate the superiority of our method.
基金项目
National Natural Science Foundation of China(62173272)
NETL
NSTL
万方数据