完整後設資料紀錄
DC 欄位語言
dc.contributor.authorHuang, Han-Hsienen_US
dc.contributor.authorWang, Tsaipeien_US
dc.date.accessioned2017-04-21T06:49:48Z-
dc.date.available2017-04-21T06:49:48Z-
dc.date.issued2015en_US
dc.identifier.isbn978-1-4799-8622-4en_US
dc.identifier.issn2325-4270en_US
dc.identifier.urihttp://hdl.handle.net/11536/135535-
dc.description.abstractIn 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.en_US
dc.language.isoen_USen_US
dc.subjectQ-learningen_US
dc.subjectTORCSen_US
dc.subjectCar Racingen_US
dc.titleLearning Overtaking and Blocking Skills in Simulated Car Racingen_US
dc.typeProceedings Paperen_US
dc.identifier.journal2015 IEEE CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND GAMES (CIG)en_US
dc.citation.spage439en_US
dc.citation.epage445en_US
dc.contributor.department資訊工程學系zh_TW
dc.contributor.departmentDepartment of Computer Scienceen_US
dc.identifier.wosnumberWOS:000376490300053en_US
dc.citation.woscount0en_US
顯示於類別:會議論文