Here we have collected all scientific publications that relates to creating an AI for Blood Bowl.
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.
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 game 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 the Fantasy Football AI (botbowl) framework that implements the core rules of Blood Bowl and includes a forward model, several OpenAI Gym environments for reinforcement learning, competition functionalities, and a web application that allows for human play. We also present Bot Bowl I, the first AI competition that will use botbowl along with baseline agents and preliminary reinforcement learning results. Additionally, we present a wealth of opportunities for future AI competitions based on botbowl.
This paper describe an hybrid agent trained to play in Fantasy Football AI which participated in the Bot Bowl III competition. The agent, MimicBot, is implemented using a specifically designed deep policy network and trained using a combination of imitation and reinforcement learning. Previous attempts in using a reinforcement learning approach in such context failed for a number of reasons, e.g. due to the intrinsic randomness in the environment and the large and uneven number of actions available, with a curriculum learning approach failing to consistently beat a randomly paying agent. Currently no machine learning approach can beat a scripted bot which makes use of the domain knowledge on the game. Our solution, thanks to an imitation learning and a hybrid decision-making process, consistently beat such scripted agents. Moreover we shed lights on how to more efficiently train in a reinforcement learning setting while drastically increasing sample efficiency. MimicBot is the winner of the Bot Bowl III competition, and it is currently the state-of-the-art solution.
Planning in the midst of chaos: how a stochastic Blood Bowl model can help to identify key planning features (2021)
For several decades now, games have become an important research ground for artificial intelligence. In addition to often present useful and complex problems, they also provide a clear framework thanks to their rules, sometimes numerous. In this article, we explore a very difficult two-players board game named Blood Bowl. This game allows the players to perform many different actions, which depend for a large part on the result of one or more dice rolls. Thus, it can be seen as a multi-action probabilistic problem driven by a Markov decision process. In this article, we present the first stochastic model of the main phase of Blood Bowl to our knowledge and the premise of a dedicated planning framework. Such a framework could offer interestinggrounds and insights for modeling high turn-wise branch factor games.