Monte-carlo planning for pathfinding in real-time strategy games

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

Abstract

In this work, we explore two Monte-Carlo planning approaches: Upper Confidence Tree (UCT) and Rapidly exploring Random Tree (RRT). These Monte-Carlo planning approaches are applied in a real-time strategy game for solving the path finding problem. The planners are evaluated using a grid-based representation of our game world. The results show that the UCT planner solves the path planning problem with significantly less search effort than the RRT planner. The game playing performance of each planner is evaluated using the mean, maximum and minimum scores in the test games. With respect to the mean scores, the RRT planner shows better performance than the UCT planner. The RRT planner achieves more maximum
scores than the UCT planner in the test games.
Original languageEnglish
Title of host publicationProceedings of the 28th Workshop of the UK Special Interest Group on Planning and Scheduling
Subtitle of host publicationjoint meeting with the 4th Italian Workshop on Planning and Scheduling: PlanSIG2010
EditorsSimone Fratini, Alfonso Gerevini, Derek Long, Alessandro Saetti
PublisherConsiglio Nazionale delle Ricerche
Pages125-139
Number of pages15
Publication statusPublished - 1 Dec 2010
Event28th Workshop of the UK Special InterestGroup on Planning and Scheduling : joint meeting with the 4th Italian Workshop on Planning and Scheduling - Brescia, Italy
Duration: 1 Dec 20102 Dec 2010
Conference number: 28

Publication series

NameProceedings of the Workshop of the UK Special Interest Group on Planning and Scheduling
PublisherConsiglio Nazionale delle Ricerche
ISSN (Print)1368-5708

Workshop

Workshop28th Workshop of the UK Special InterestGroup on Planning and Scheduling
Abbreviated titlePlanSIG2010
Country/TerritoryItaly
CityBrescia
Period1/12/102/12/10

Fingerprint

Dive into the research topics of 'Monte-carlo planning for pathfinding in real-time strategy games'. Together they form a unique fingerprint.

Cite this