On Gradient-Based Learning in Continuous Games
Authors:
- Eric MazumdarEMEric Mazumdar
- Lillian J. RatliffLRLillian J. Ratliff
- S. Shankar SastrySSS. Shankar Sastry
- 1 January 2020
- journal article
- research article
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Mathematics of Data Science
- Vol. 2 (1) , 103-131
Abstract
We introduce a general framework for competitive gradient-based learning that encompasses a wide breadth of multiagent learning algorithms, and analyze the limiting behavior of competitive gradient...Keywords
All Related Versions
Funding Information
- Defense Advanced Research Projects Agency (FA8750-18-C-0101)
- National Science Foundation (CNS:1656873)
This publication has 23 references indexed in Scilit:
- Multiple equilibria and limit cycles in evolutionary games with Logit DynamicsGames and Economic Behavior, 2012
- A survey of random processes with reinforcementProbability Surveys, 2007
- Individual Q-Learning in Normal Form GamesSIAM Journal on Control and Optimization, 2005
- Potential GamesGames and Economic Behavior, 1996
- A Dynamical System Approach to Stochastic ApproximationsSIAM Journal on Control and Optimization, 1996
- Dynamics of Morse-Smale urn processesErgodic Theory and Dynamical Systems, 1995
- Nonconvergence to Unstable Points in Urn Models and Stochastic ApproximationsThe Annals of Probability, 1990
- A Structural Stability TheoremAnnals of Mathematics, 1971
- Differentiable dynamical systemsBulletin of the American Mathematical Society, 1967
- Existence and Uniqueness of Equilibrium Points for Concave N-Person GamesEconometrica, 1965