Differentiable Arbitrating in Zero-sum Markov Games
Abstract
We initiate the study of how to perturb the reward in a zero-sum Markov game with two players to induce a desirable Nash equilibrium, namely arbitrating. Such a problem admits a bi-level optimization formulation. The lower level requires solving the Nash equilibrium under a given reward function, which makes the overall problem challenging to optimize in an end-to-end way. We propose a backpropagation scheme that differentiates through the Nash equilibrium, which provides the gradient feedback for the upper level. In particular, our method only requires a black-box solver for the (regularized) Nash equilibrium (NE). We develop the convergence analysis for the proposed framework with proper black-box NE solvers and demonstrate the empirical successes in two multi-agent reinforcement learning (MARL) environments.
Keywords
Cite
@article{arxiv.2302.10058,
title = {Differentiable Arbitrating in Zero-sum Markov Games},
author = {Jing Wang and Meichen Song and Feng Gao and Boyi Liu and Zhaoran Wang and Yi Wu},
journal= {arXiv preprint arXiv:2302.10058},
year = {2023}
}