Blood Bowl: The Next Board Game Challenge for AI

Niels Justesen, Sebastian Risi, Julian Togelius

Research output: Conference Article in Proceeding or Book/Report chapterConference abstract in proceedingsResearchpeer-review


We propose the popular board game Blood Bowl as a new challenge for Artificial Intelligence (AI). Blood Bowl is a fully-observable, stochastic, turn-based, modern-style board game with a grid-based playing board. At first sight, the game ought to be approachable by numerous game-playing algorithms. However, as all pieces on the board belonging to a player can be moved several times each turn, the turn-wise branching factor becomes overwhelming for traditional algorithms. Additionally, scoring points in the game is rare and difficult, which makes it hard to design heuristics for search algorithms or apply reinforcement learning. We present our work in progress on a game engine that implements the core rules of Blood Bowl with a forward model and a reinforcement learning interface. We plan to release the engine as open source and use it to facilitate future AI competitions.
Original languageEnglish
Title of host publicationBlood Bowl: The Next Board Game Challenge for AI
Number of pages2
PublisherAssociation for Computing Machinery
Publication date2018
Publication statusPublished - 2018
EventFDG Workshop on Tabletop Games - Malmö, Sweden
Duration: 7 Aug 201810 Aug 2018


WorkshopFDG Workshop on Tabletop Games
Internet address


  • Artificial Intelligence
  • Board Games
  • Reinforcement Learning
  • Stochastic Systems
  • Game Engine Development


Dive into the research topics of 'Blood Bowl: The Next Board Game Challenge for AI'. Together they form a unique fingerprint.

Cite this