Fitness shaping for multiple teams
Fitness shaping for multiple teams
复制标题
DOI：
10.1145/3512290.3528829
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
J. Cook;Kagan Tumer
中科院分区：
文献类型：
--
作者：
J. Cook;Kagan Tumer
协同进化算法已经有效地训练了多智能体团队来共同解决复杂问题。然而，在许多现实世界的应用程序中，环境或代理功能的变化需要代理与多个不同的团队一起工作。在本文中，我们提供了一个反事实的状态为基础的形健身评估，提供了一个代理特定的信号，促进各种团队的有效合作。导致这一结果的关键见解是，多个团队的形状适合度可以聚合，因为这些表现是相互独立的。因此，这种方法会产生一个单一的信号，可以捕获多个团队中座席的表现。我们表明，这种方法提供了显着的改进，在学习鲁棒的合作行为的标准多智能体健身形的方法。
Coevolutionary algorithms have effectively trained multiagent teams to collectively solve complex problems. However, in many real-world applications, changes to the environment or agent functionality require agents to function well with multiple different teams. In this paper, we provide a counterfactual-state-based shaped fitness evaluation that provides an agent-specific signal that promotes effective cooperation across a variety of teams. The key insight leading to this result is that the shaped fitnesses across multiple teams can be aggregated because those performances are independent of each other. As a result, this approach leads to a single signal that captures an agent's performance across multiple teams. We show that this method provides significant improvement over standard multiagent fitness-shaped methods in learning robust cooperative behavior.