Diverse Behavior Is What Game AI Needs: Generating Varied Human-Like Playing Styles Using Evolutionary Multi-Objective Deep Reinforcement Learning
arXiv:1910.09022
Abstract
this paper has been withdrawn
1. there is some discrepancy between some contributors with respect to the order of the authors; 2. the paper is rather "raw" - significant effort and improvement in terms of the paper's language and structure are needed to make it ready for publication