Specification-Guided Learning of Nash Equilibria with High Social Welfare. (arXiv:2206.03348v1 [cs.GT])

Reinforcement learning has been shown to be an effective strategy for
automatically training policies for challenging control problems. Focusing on
non-cooperative multi-agent systems, we propose a novel reinforcement learning
framework for training joint policies that form a Nash equilibrium. In our
approach, rather than providing low-level reward functions, the user provides
high-level specifications that encode the objective of each agent. Then, guided
by the structure of the specifications, our algorithm searches over policies to
identify one that provably forms an …

arxiv equilibria learning social