论文标题
逻辑团队Q学习：合作MARL中有因式政策的方法
Logical Team Q-learning: An approach towards factored policies in cooperative MARL
论文作者
论文摘要
我们应对在合作MARL情景中学习的学习构成政策的挑战。特别是，我们考虑了一组代理团队合作以优化普通成本的情况。目的是获得确定每个代理人的个体行为的有因式的策略，以使所得的联合政策是最佳的。这项工作的主要贡献是逻辑团队Q学习（LTQL）的引入。 LTQL不依赖于对环境的假设，因此通常适用于任何协作的MARL场景。我们将LTQL作为随机近似推导为我们在这项工作中介绍的动态编程方法。我们通过提供说明主张的实验（在表格和深度设置中）来结束论文。
We address the challenge of learning factored policies in cooperative MARL scenarios. In particular, we consider the situation in which a team of agents collaborates to optimize a common cost. The goal is to obtain factored policies that determine the individual behavior of each agent so that the resulting joint policy is optimal. The main contribution of this work is the introduction of Logical Team Q-learning (LTQL). LTQL does not rely on assumptions about the environment and hence is generally applicable to any collaborative MARL scenario. We derive LTQL as a stochastic approximation to a dynamic programming method we introduce in this work. We conclude the paper by providing experiments (both in the tabular and deep settings) that illustrate the claims.
