Rinascimento: Optimising Statistical Forward Planning Agents for Playing Splendor
This work provides a new customizable game-based benchmark for AI research, but it is incremental as it builds on existing statistical forward planning methods without major breakthroughs.
The authors introduced Rinascimento, a parameterized partially-observable multiplayer board game framework to serve as a benchmark for AI development, and provided baseline agents with hyper-parameter tuning that significantly influenced performance, though no concrete numerical results were reported.
Game-based benchmarks have been playing an essential role in the development of Artificial Intelligence (AI) techniques. Providing diverse challenges is crucial to push research toward innovation and understanding in modern techniques. Rinascimento provides a parameterised partially-observable multiplayer card-based board game, these parameters can easily modify the rules, objectives and items in the game. We describe the framework in all its features and the game-playing challenge providing baseline game-playing AIs and analysis of their skills. We reserve to agents' hyper-parameter tuning a central role in the experiments highlighting how it can heavily influence the performance. The base-line agents contain several additional contribution to Statistical Forward Planning algorithms.