Exploring Adaptive MCTS with TD Learning in miniXCOM

Simple item page
dc.contributor.authorSaadat, Kimiya
dc.contributor.authorZhao, Richard
dc.date.accessioned2023-03-09T16:11:37Z
dc.date.available2023-03-09T16:11:37Z
dc.date.issued2022-10-24
dc.descriptionProceedings of the Ninth AIIDE Workshop on Experimental Artificial Intelligence in Game (EXAG 2022)en_US
dc.description.abstractIn recent years, Monte Carlo tree search (MCTS) has achieved widespread adoption within the game community. Its use in conjunction with deep reinforcement learning has produced success stories in many applications. While these approaches have been implemented in various games, from simple board games to more complicated video games such as StarCraft, the use of deep neural networks requires a substantial training period. In this work, we explore on-line adaptivity in MCTS without requiring pre-training. We present MCTS-TD, an adaptive MCTS algorithm improved with temporal difference learning. We demonstrate our new approach on the game miniXCOM, a simplified version of XCOM, a popular commercial franchise consisting of several turn-based tactical games, and show how adaptivity in MCTS-TD allows for improved performances against opponents.en_US
dc.identifier.citationSaadat, K., and Zhao, R. (2022, October 24-25). Exploring Adaptive MCTS with TD Learning in miniXCOM [Paper presentation]. AIIDE Workshop on Experimental AI in Games (EXAG) 2022, Pomona, CA, United States.en_US
dc.identifier.urihttp://hdl.handle.net/1880/115906
dc.identifier.urihttps://dx.doi.org/10.11575/PRISM/40781
dc.language.isoengen_US
dc.publisher.departmentComputer Scienceen_US
dc.publisher.facultyScienceen_US
dc.publisher.hasversionacceptedVersionen_US
dc.publisher.institutionUniversity of Calgaryen_US
dc.rightsUnless otherwise indicated, this material is protected by copyright and has been made available with authorization from the copyright owner. You may use this material in any way that is permitted by the Copyright Act or through licensing that has been assigned to the document. For uses that are not allowable under copyright legislation or licensing, you are required to seek permission.en_US
dc.subjectArtificial Intelligenceen_US
dc.subjectMonte Carlo Tree Searchen_US
dc.subjectReinforcement Learningen_US
dc.titleExploring Adaptive MCTS with TD Learning in miniXCOMen_US
dc.typeconference proceedingsen_US
ucalgary.item.requestcopytrueen_US
ucalgary.scholar.levelFacultyen_US
ucalgary.scholar.levelGraduateen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
2022exag-adaptive_mcts.pdf
Size:
461.87 KB
Format:
Adobe Portable Document Format
Description:
Main article
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.92 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Science Research & Publications