Extracting tactics learned from self-play in general games

Dennis J. N. J. Soemers, Spyridon Samothrakis, Éric Piette, Matthew Stephenson

Research output: Contribution to journalArticlepeer-review


Local, spatial state-action features can be used to effectively train linear policies from self-play in a wide variety of board games. Such policies can play games directly, or be used to bias tree search agents. However, the resulting feature sets can be large, with a significant amount of overlap and redundancies between features. This is a problem for two reasons. Firstly, large feature sets can be computationally expensive, which reduces the playing strength of agents based on them. Secondly, redundancies and correlations between features impair the ability for humans to analyse, interpret, or understand tactics learned by the policies. We look towards decision trees for their ability to perform feature selection, and serve as interpretable models. Previous work on distilling policies into decision trees uses states as inputs, and distributions over the complete action space as outputs. In contrast, we propose and evaluate a variety of decision tree types, which take state-action pairs as inputs, and provide various different types of outputs on a per-action basis. An empirical evaluation over 43 different board games is presented, and two of those games are used as case studies where we attempt to interpret the discovered features.

Original languageEnglish
Pages (from-to)277-298
Number of pages22
JournalInformation Sciences
Early online date30 Dec 2022
Publication statusPublished - May 2023
Externally publishedYes


  • Decision trees
  • Explainable AI
  • Feature selection
  • Games


Dive into the research topics of 'Extracting tactics learned from self-play in general games'. Together they form a unique fingerprint.

Cite this