Playing Catan with Cross-dimensional Neural Network

2020/08/17 by Quentin Gendre, Gendre, Quentin, Tomoyuki Kaneko +1
Computer Science · Economics, Econometrics and Finance · #Artificial Intelligence (cs.AI) #Artificial Intelligence in Games #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Reinforcement Learning in Robotics #Sports Analytics and Performance

paper · pdf · doi:10.48550/arxiv.2008.07079

openalex publication_date 2020/08/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Catan is a strategic board game having interesting properties, including multi-player, imperfect information, stochastic, complex state space structure (hexagonal board where each vertex, edge and face has its own features, cards for each player, etc), and a large action space (including negotiation). Therefore, it is challenging to build AI agents by Reinforcement Learning (RL for short), without domain knowledge nor heuristics. In this paper, we introduce cross-dimensional neural networks to handle a mixture of information sources and a wide variety of outputs, and empirically demonstrate that the network dramatically improves RL in Catan. We also show that, for the first time, a RL agent can outperform jsettler, the best heuristic agent available.

Citations

• Playing Atari with Deep Reinforcement Learning
• Suphx: Mastering Mahjong with Deep Reinforcement Learning

Related

• Deep Reinforcement Learning to Master the Asymmetric Strategy of Baghchal
• DanZero+: Dominating the GuanDan Game through Reinforcement Learning
• Mastering the Game of Guandan with Deep Reinforcement Learning and Behavior Regulating
• Application of Self-Play Reinforcement Learning to a Four-Player Game of Imperfect Information
• From Images to Connections: Can DQN with GNNs learn the Strategic Game of Hex?