Baselines for Joint-Action Reinforcement Learning of Coordination in Cooperative Multi-agent Systems

Abstract

AbstractA common assumption for the study of reinforcement learning of coordination is that agents can observe each other’s actions (so-called joint-action learning). We present in this paper a number of simple joint-action learning algorithms and show that they perform very well when compared against more complex approaches such as OAL [1], while still maintaining convergence guarantees. Based on the empirical results, we argue that these simple algorithms should be used as baselines for any future research on joint-action learning of coordination.KeywordsReinforcement LearnJoint ActionMultiagent SystemOptimal ActionStochastic GameThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.