DeepAI AI Chat
Log In Sign Up

Polymatrix Competitive Gradient Descent

by   Jeffrey Ma, et al.
Georgia Institute of Technology
University of California, San Diego
California Institute of Technology

Many economic games and machine learning approaches can be cast as competitive optimization problems where multiple agents are minimizing their respective objective function, which depends on all agents' actions. While gradient descent is a reliable basic workhorse for single-agent optimization, it often leads to oscillation in competitive optimization. In this work we propose polymatrix competitive gradient descent (PCGD) as a method for solving general sum competitive optimization involving arbitrary numbers of agents. The updates of our method are obtained as the Nash equilibria of a local polymatrix approximation with a quadratic regularization, and can be computed efficiently by solving a linear system of equations. We prove local convergence of PCGD to stable fixed points for n-player general-sum games, and show that it does not require adapting the step size to the strength of the player-interactions. We use PCGD to optimize policies in multi-agent reinforcement learning and demonstrate its advantages in Snake, Markov soccer and an electricity market game. Agents trained by PCGD outperform agents trained with simultaneous gradient descent, symplectic gradient adjustment, and extragradient in Snake and Markov soccer games and on the electricity market game, PCGD trains faster than both simultaneous gradient descent and the extragradient method.


page 9

page 17


O(1/T) Time-Average Convergence in a Generalization of Multiagent Zero-Sum Games

We introduce a generalization of zero-sum network multiagent matrix game...

COLA: Consistent Learning with Opponent-Learning Awareness

Learning in general-sum games can be unstable and often leads to sociall...

The Mechanics of n-Player Differentiable Games

The cornerstone underpinning deep learning is the guarantee that gradien...

Minmax Optimization: Stable Limit Points of Gradient Descent Ascent are Locally Optimal

Minmax optimization, especially in its general nonconvex-nonconcave form...

Differentiable Game Mechanics

Deep learning is built on the foundational guarantee that gradient desce...

Competitive Mirror Descent

Constrained competitive optimization involves multiple agents trying to ...

Competitive Gradient Optimization

We study the problem of convergence to a stationary point in zero-sum ga...