# Playing Catan with Cross-dimensional Neural Network

arXiv: https://arxiv.org/abs/2008.07079 · HTML: https://mlsanity.com/paper/2008.07079/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Aug 2020.

## Built on by (most cited first, 2 of 2)

- [Agents of Change: Self-Evolving LLM Agents for Strategic Planning](https://mlsanity.com/paper/2506.04651/) (2025)
- [Adversarial Imitation Learning On Aggregated Data](https://mlsanity.com/paper/2311.08568/) (2023)

## Abstract (arXiv)

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.