Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning

    Anuj Mahajan 1 Mikayel Samvelyan 2 Lei Mao 3 Viktor Makoviychuk 3 Animesh Garg 3 Jean Kossaifi 3
             Shimon Whiteson 1 Yuke Zhu 3 Animashree Anandkumar 3

             Abstract                arise in single-agent reinforcement learning (RL), includ-
    Reinforcement Learning in large action spaces is     ing exponential growth of the action space in the number
    a challenging problem. Cooperative multi-agent    ...