A Fast Evolutionary adaptation for MCTS in Pommerman
This work addresses the challenge of efficient AI in complex multi-agent games like Pommerman, representing an incremental improvement by hybridizing existing methods.
The paper tackled the problem of high search complexity in multi-agent games by proposing a novel Evolutionary Monte Carlo Tree Search (FEMCTS) agent for Pommerman, which significantly outperforms Rolling Horizon Evolutionary Algorithm in high observability settings and matches or exceeds MCTS performance in many cases.
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.