The development of a simulated car racing controller based on Monte-Carlo tree search

Jia Hao Hou, Tsaipei Wang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Ever since its introduction, Monte Carlo Tree Search (MCTS) has shown very good performances on a number of games, most of which are turn-based zero-sum games. More recently, researchers have also started to expand the application of MCTS to other types of games. This paper proposes a new framework of applying MCTS to the game of simulated car racing. We choose to build the search tree in a discretized game-state space and then determine the action from the selected target game state. This allows us to avoid the need to discretize the action space. In addition, we are able to incorporate some heuristics on driving strategies naturally. The resulting controller shows very competitive performance in the open-source racing game TORCS.

Original languageEnglish
Title of host publicationTAAI 2016 - 2016 Conference on Technologies and Applications of Artificial Intelligence, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages104-109
Number of pages6
ISBN (Electronic)9781509057320
DOIs
StatePublished - 16 Mar 2017
Event2016 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2016 - Hsinchu, Taiwan
Duration: 25 Nov 201627 Nov 2016

Publication series

NameTAAI 2016 - 2016 Conference on Technologies and Applications of Artificial Intelligence, Proceedings

Conference

Conference2016 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2016
Country/TerritoryTaiwan
CityHsinchu
Period25/11/1627/11/16

Keywords

  • MCTS
  • Simulated Car Racing
  • TORCS

Fingerprint

Dive into the research topics of 'The development of a simulated car racing controller based on Monte-Carlo tree search'. Together they form a unique fingerprint.

Cite this