标题: Learning Overtaking and Blocking Skills in Simulated Car Racing
作者: Huang, Han-Hsien
Wang, Tsaipei
资讯工程学系
Department of Computer Science
关键字: Q-learning;TORCS;Car Racing
公开日期: 2015
摘要: In this paper we describe the analysis of using Q-learning to acquire overtaking and blocking skills in simulated car racing games. Overtaking and blocking are more complicated racing skills compared to driving alone, and past work on this topic has only touched overtaking in very limited scenarios. Our work demonstrates that a driving AI agent can learn overtaking and blocking skills via machine learning, and the acquired skills are applicable when facing different opponent types and track characteristics, even on actual built-in tracks in TORCS.
URI: http://hdl.handle.net/11536/135535
ISBN: 978-1-4799-8622-4
ISSN: 2325-4270
期刊: 2015 IEEE CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND GAMES (CIG)
起始页: 439
结束页: 445
显示于类别:Conferences Paper