Playing Various Strategies in Dominion with Deep Reinforcement Learning


  • Jasper Gerigk University of Toronto
  • Steve Engels University of Toronto



Reinforcement Learning, Deck-Building Game, Geometric Deep Learning, Game AI


Deck-building games, like Dominion, present an unsolved challenge for game AI research. The complexity arising from card interactions and the relative strength of strategies depending on the game configuration result in computer agents being limited to simple strategies. This paper describes the first application of recent advances in Geometric Deep Learning to deck-building games. We utilize a comprehensive multiset-based game representation and train the policy using a Soft Actor-Critic algorithm adapted to support variable-size sets of actions. The proposed model is the first successful learning-based agent that makes all decisions without relying on heuristics and supports a broader set of game configurations. It exceeds the performance of all previous learning-based approaches and is only outperformed by search-based approaches in certain game configurations. In addition, the paper presents modifications that induce agents to exhibit novel human-like play strategies. Finally, we show that learning strong strategies based on card combinations requires a reinforcement learning algorithm capable of discovering and executing a precise strategy while ignoring simpler suboptimal policies with higher immediate rewards.




How to Cite

Gerigk, J., & Engels, S. (2023). Playing Various Strategies in Dominion with Deep Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 19(1), 224-232.