Balancing Two-Player Stochastic Games with Soft Q-Learning

back to our research

Balancing Two-Player Stochastic Games with Soft Q-Learning

July 13 - 19, 2018 Stockholm, Sweden

27th International Joint Conference on Artificial Intelligence and the 23rd European Conference on Artificial Intelligence (IJCAI-ECAI 2018)

Authors: Jordi Grau-Moya (, Felix Leibfried (, Haitham Bou-Ammar (

Abstract: Within the context of video games the notion of perfectly rational agents can be undesirable as it leads to uninteresting situations, where humans face tough adversarial decision makers. Current frameworks for stochastic games and reinforcement learning prohibit tuneable strategies as they seek optimal performance. In this paper, we enable such tuneable behaviour by generalising soft Q-learning to stochastic games, where more than one agent interact strategically. We contribute both theoretically and empirically. On the theory side, we show that games with soft Q-learning exhibit a unique value and generalise team games and zero-sum games far beyond these two extremes to cover a continuous spectrum of gaming behaviour. Experimentally, we show how tuning agents' constraints affect performance and demonstrate, through a neural network architecture, how to reliably balance games with high-dimensional representations.

Game Theory

Reinforcement Learning

High-Dimensional Representation

See paper

Join us to make AI that will change the world

join our team