Dominion: A New Frontier for AI Research

TL;DR

This paper introduces Dominion as a new benchmark for AI research, providing a large dataset of games and a baseline RL bot to advance reinforcement learning in complex strategic environments.

Contribution

It presents the Dominion Online Dataset and a baseline RL bot, establishing a new platform for testing and developing AI algorithms in complex tabletop games.

Findings

The dataset contains over 2 million games.

The RL baseline outperforms heuristic bots.

The RL bot is competitive against the strongest existing bot.

Abstract

In recent years, machine learning approaches have made dramatic advances, reaching superhuman performance in Go, Atari, and poker variants. These games, and others before them, have served not only as a testbed but have also helped to push the boundaries of AI research. Continuing this tradition, we examine the tabletop game Dominion and discuss the properties that make it well-suited to serve as a benchmark for the next generation of reinforcement learning (RL) algorithms. We also present the Dominion Online Dataset, a collection of over 2,000,000 games of Dominion played by experienced players on the Dominion Online webserver. Finally, we introduce an RL baseline bot that uses existing techniques to beat common heuristic-based bots, and shows competitive performance against the previously strongest bot, Provincial.