There are some methods to get the NE,i have used the backward induction with Fixed point theorem in my paper. Now i wanna know how to get it with DRL.Thanks.
Some good related literature to your query :: https://medium.com/dataseries/how-modern-game-theory-is-influencing-multi-agent-reinforcement-learning-systems-part-ii-4f47166d0fe6
https://arxiv.org/pdf/2001.06487.pdf
Article The Nash Equilibrium: A Perspective
Chapter Game Theory and Multi-agent Reinforcement Learning