Learning in Nonzero-Sum Stochastic Games with Potentials

David Mguni 1 Yutong Wu 2 Yali Du 3 Yaodong Yang 1 3 Ziyi Wang 2 Minne Li 3 Ying Wen 4 Joel Jennings 1
                       Jun Wang 3

            Abstract                autonomous vehicles seeking to arrive at their individual
   Multi-agent reinforcement learning (MARL) has       destinations must avoid colliding with other vehicles. There-
   become effective in tackling discrete cooperative     fore to perform their task the agen ...