Balancing Two-Player Stochastic Games with Soft Q-Learning
Balancing Two-Player Stochastic Games with Soft Q-Learning
Jordi Grau-Moya, Felix Leibfried, Haitham Bou-Ammar
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Main track. Pages 268-274.
https://doi.org/10.24963/ijcai.2018/37
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.
Keywords:
Agent-based and Multi-agent Systems: Multi-agent Learning
Machine Learning: Reinforcement Learning
Agent-based and Multi-agent Systems: Agent Theories and Models
Machine Learning Applications: Applications of Reinforcement Learning