A Fast Evolutionary adaptation for MCTS in Pommerman

TL;DR

This paper introduces FEMCTS, a novel AI agent combining Evolutionary Algorithms and Monte Carlo Tree Search to improve performance in Pommerman, especially under high observability conditions, outperforming existing methods.

Contribution

The paper presents FEMCTS, a new hybrid algorithm that enhances game-playing AI by integrating evolutionary strategies with MCTS, demonstrating superior performance in Pommerman.

Findings

FEMCTS outperforms RHEA in high observability settings.

FEMCTS performs nearly as well as MCTS across most game seeds.

FEMCTS surpasses MCTS in some specific cases.

Abstract

Artificial Intelligence, when amalgamated with games makes the ideal structure for research and advancing the field. Multi-agent games have multiple controls for each agent which generates huge amounts of data while increasing search complexity. Thus, we need advanced search methods to find a solution and create an artificially intelligent agent. In this paper, we propose our novel Evolutionary Monte Carlo Tree Search (FEMCTS) agent which borrows ideas from Evolutionary Algorthims (EA) and Monte Carlo Tree Search (MCTS) to play the game of Pommerman. It outperforms Rolling Horizon Evolutionary Algorithm (RHEA) significantly in high observability settings and performs almost as well as MCTS for most game seeds, outperforming it in some cases.