Cooperative Exploration for Multi-Agent Deep Reinforcement Learning

             Iou-Jen Liu 1 Unnat Jain   1
                              Raymond A. Yeh 1 Alexander G. Schwing 1

              Abstract                (MADDPG) (Lowe et al., 2017), and counterfactual multi-
    Exploration is critical for good results in deep re-    agent policy gradients (COMA) (Foerster et al., 2018) have
    inforcement learning and has attracted much at-       been developed. Those methods excel in a multi- ...