Deep Fictitious Play for Finding Markovian Nash Equilibrium in Multi-Agent Games
By Jiequn Han, Ruimeng Hu. 2019
52 citations recorded by the source corpus.
We propose a deep neural network-based algorithm to identify the Markovian Nash equilibrium of general large $N$-player stochastic differential games. Following the idea of fictitious play, we recast the $N$-player game into $N$ decoupled decision problems (one for each player) and solve them iteratively. The individual decision problem is characterized by a semilinear Hamilton-Jacobi-Bellman equation, to solve which we employ the recently developed deep BSDE method. The resulted algorithm can solve large $N$-player games for which conventional numerical methods would suffer from the curse of dimensionality. Multiple numerical examples involving identical or heterogeneous agents, with risk-neutral or risk-sensitive objectives, are tested to validate the accuracy of the proposed algorithm in large group games. Even for a fifty-player game with the presence of common noise, the proposed algorithm still finds the approximate Nash equilibrium accurately, which, to our best knowledge, is difficult to achieve by other numerical algorithms.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
Citations in the corpus
- Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization (2021, background): “…increasingly significant interests from AI researchers (Heinrich & Silver, 2016; Lanctot et al., 2017; Foerster et al., 2018; Kamra et al., 2019; Han & Hu, 2019; Bai & Jin, 2020; Perolat et al., 2020): many existing works studied how to design practical multi-agent reinforcement learning…”