Timezone: »

 
Poster
Learning to Optimize Differentiable Games
Xuxi Chen · Nelson Vadori · Tianlong Chen · Zhangyang “Atlas” Wang

Thu Jul 27 04:30 PM -- 06:00 PM (PDT) @ Exhibit Hall 1 #618
in Poster Session 6 »

Many machine learning problems can be abstracted in solving game theory formulations and boil down to optimizing nested objectives, such as generative adversarial networks (GANs) and multi-agent reinforcement learning. Solving these games requires finding their stable fixed points or Nash equilibrium. However, existing algorithms for solving games suffer from empirical instability, hence demanding heavy ad-hoc tuning in practice. To tackle these challenges, we resort to the emerging scheme of Learning to Optimize (L2O), which discovers problem-specific efficient optimization algorithms through data-driven training. Our customized L2O framework for differentiable game theory problems, dubbed ``Learning to Play Games" (L2PG), seeks a stable fixed point solution, by predicting the fast update direction from the past trajectory, with a novel gradient stability-aware, sign-based loss function. We further incorporate curriculum learning and self-learning to strengthen the empirical training stability and generalization of L2PG. On test problems including quadratic games and GANs, L2PG can substantially accelerate the convergence, and demonstrates a remarkably more stable trajectory. Codes are available at https://github.com/VITA-Group/L2PG.

[ PDF] 

Author Information

Xuxi Chen (University of Texas at Austin)
Nelson Vadori (J.P. Morgan AI Research)
Tianlong Chen (PostDoc - MIT/Harvard; Incoming Assistant Professor - UNC Chapel Hill)
Zhangyang “Atlas” Wang (University of Texas at Austin)

More from the Same Authors