Enhancements for Real-Time Monte-Carlo Tree Search in General Video Game Playing

Dennis J. N. J. Soemers*, Chiara F. Sironi, Torsten Schuster, Mark H. M. Winands

*Corresponding author for this work

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

15 Citations (Web of Science)
24 Downloads (Pure)


General Video Game Playing (GVGP) is a field of Artificial Intelligence where agents play a variety of real-time video games that are unknown in advance. This limits the use of domain-specific heuristics. Monte-Carlo Tree Search (MCTS) is a search technique for game playing that does not rely on domain-specific knowledge. This paper discusses eight enhancements for MCTS in GVGP; Progressive History, N-Gram Selection Technique, Tree Reuse, Breadth-First Tree Initialization, Loss Avoidance, Novelty-Based Pruning, Knowledge-Based Evaluations, and Deterministic Game Detection. Some of these are known from existing literature, and are either extended or introduced in the context of GVGP, and some are novel enhancements for MCTS. Most enhancements are shown to provide statistically significant increases in win percentages when applied individually. When combined, they increase the average win percentage over sixty different games from 31.0% to 48.4% in comparison to a vanilla MCTS implementation, approaching a level that is competitive with the best agents of the GVG-AI competition in 2015.
Original languageEnglish
Title of host publication2016 IEEE Conference on Computational Intelligence and Games (CIG)
Number of pages8
Publication statusPublished - Sept 2016
Event2016 IEEE Conference on Computational Intelligence and Games (CIG) - Petros M. Nomikos Conference Centre, Santorini, Greece
Duration: 20 Sept 201623 Sept 2016

Publication series

SeriesIEEE Conference on Computational Intelligence and Games


Conference2016 IEEE Conference on Computational Intelligence and Games (CIG)

Cite this