Transformer引导的协同进化：改进多智能体对抗团队博弈中的团队选择
Transformer Guided Coevolution: Improved Team Selection in Multiagent Adversarial Team Games
AI总结：
本文提出BERTeam算法，结合基于transformer的掩码语言模型与协同进化深度强化学习，解决多智能体对抗团队博弈中的团队选择问题，实验证明其能学习到优于MCAA的团队组合。
摘要：
我们考虑多智能体对抗团队博弈中的团队选择问题。我们提出了BERTeam，这是一种新颖的算法，使用基于transformer的深度神经网络，并通过掩码语言模型训练，从训练好的种群中选择最佳球员团队。我们将其与协同进化深度强化学习相结合，后者训练多样化的个体球员供选择。我们在多智能体对抗游戏Marine Capture-The-Flag中测试了该算法，发现BERTeam能学习到非平凡的团队组合，在面对未见过的对手时表现良好。对于该游戏，我们发现BERTeam优于MCAA，这是一种同样优化团队选择的算法。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
