Transformer Guided Coevolution: Improved Team Selection in Multiagent Adversarial Team Games
This addresses team composition optimization for multiagent systems in adversarial environments, representing an incremental improvement over existing methods.
The paper tackles team selection in multiagent adversarial games by proposing BERTeam, a transformer-based algorithm integrated with coevolutionary deep reinforcement learning, which outperforms the MCAA algorithm in the Marine Capture-The-Flag game.
We consider the problem of team selection within multiagent adversarial team games. We propose BERTeam, a novel algorithm that uses a transformer-based deep neural network with Masked Language Model training to select the best team of players from a trained population. We integrate this with coevolutionary deep reinforcement learning, which trains a diverse set of individual players to choose from. We test our algorithm in the multiagent adversarial game Marine Capture-The-Flag, and find that BERTeam learns non-trivial team compositions that perform well against unseen opponents. For this game, we find that BERTeam outperforms MCAA, an algorithm that similarly optimizes team selection.