ERMAS: Learning Policies Robust to Reality Gaps in Multi-Agent Simulations

Policies for real-world multi-agent problems, such as optimal taxation, can be learned in multi-agent simulations with AI agents that emulate humans. However, simulations can suffer from reality gaps as humans often act suboptimally or optimize for different objectives (i.e., bounded rationality). We introduce $\epsilon$-Robust Multi-Agent Simulation (ERMAS), a robust optimization framework to learn AI policies that are robust to such multi-agent reality gaps. The objective of ERMAS theoretically guarantees robustness to the $\epsilon$-Nash equilibria of other agents – that is, robustness to behavioral deviations with a regret of at most$\epsilon$. ERMAS efficiently solves a first-order approximation of the robustness objective using meta-learning methods. We show that ERMAS yields robust policies for repeated bimatrix games and optimal adaptive taxation in economic simulations, even when baseline notions of robustness are uninformative or intractable. In particular, we show ERMAS can learn tax policies that are robust to changes in agent risk aversion, improving policy objectives (social welfare) by up to 15% in complex spatiotemporal simulations using the AI Economist (Zheng et al., 2020).