Learning overtaking and blocking skills in simulated car racing

Han Hsien Huang, Tsaipei Wang

研究成果: Conference contribution同行評審

10 引文 斯高帕斯(Scopus)

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.

原文English
主出版物標題2015 IEEE Conference on Computational Intelligence and Games, CIG 2015 - Proceedings
發行者Institute of Electrical and Electronics Engineers Inc.
頁面439-445
頁數7
ISBN(電子)9781479986217
DOIs
出版狀態Published - 4 11月 2015
事件2015 IEEE Conference on Computational Intelligence and Games, CIG 2015 - Tainan, 台灣
持續時間: 31 8月 20152 9月 2015

出版系列

名字2015 IEEE Conference on Computational Intelligence and Games, CIG 2015 - Proceedings

Conference

Conference2015 IEEE Conference on Computational Intelligence and Games, CIG 2015
國家/地區台灣
城市Tainan
期間31/08/152/09/15

指紋

深入研究「Learning overtaking and blocking skills in simulated car racing」主題。共同形成了獨特的指紋。

引用此