DelAC: A Multi-agent Reinforcement Learning of Team-Symmetric Stochastic Games
For researchers in multi-agent reinforcement learning, this work provides a theoretical foundation and practical algorithm for team-symmetric games, though the performance gains are demonstrated only in simulation.
This paper proves the existence of team-symmetric Nash equilibria in team-symmetric stochastic games and proposes a multi-agent reinforcement learning algorithm that outperforms existing methods in simulations.
In this paper we study team-symmetric games with $m\ge 2$ teams. Players within a team have symmetric identity and have a common payoff function. We show that team-symmetric games always have a team-symmetric Nash equilibrium. We develop and solve a linear complementarity problem of team-symmetric Nash equilibria. We propose an actor-critic based multi-agent reinforcement learning algorithm for team-symmetric games. Through simulations, we show that this multi-agent reinforcement learning algorithm performs much better than many existing algorithms.