Timezone: »

Large-Scale Multi-Agent Deep FBSDEs
Tianrong Chen · Ziyi Wang · Ioannis Exarchos · Evangelos Theodorou

Wed Jul 21 07:35 AM -- 07:40 AM (PDT) @

In this paper we present a scalable deep learning framework for finding Markovian Nash Equilibria in multi-agent stochastic games using fictitious play. The motivation is inspired by theoretical analysis of Forward Backward Stochastic Differential Equations and their implementation in a deep learning setting, which is the source of our algorithm's sample efficiency improvement. By taking advantage of the permutation-invariant property of agents in symmetric games, the scalability and performance is further enhanced significantly. We showcase superior performance of our framework over the state-of-the-art deep fictitious play algorithm on an inter-bank lending/borrowing problem in terms of multiple metrics. More importantly, our approach scales up to 3000 agents in simulation, a scale which, to the best of our knowledge, represents a new state-of-the-art. We also demonstrate the applicability of our framework in robotics on a belief space autonomous racing problem.

Author Information

Tianrong Chen (Georgia Institute of Technology)
Ziyi Wang (Georgia Institute of Technology)
Ioannis Exarchos (Stanford University)
Evangelos Theodorou (Georgia Tech)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors