References & Citations
Computer Science > Machine Learning
Title: Finite-sample Guarantees for Nash Q-learning with Linear Function Approximation
(Submitted on 1 Mar 2023)
Abstract: Nash Q-learning may be considered one of the first and most known algorithms in multi-agent reinforcement learning (MARL) for learning policies that constitute a Nash equilibrium of an underlying general-sum Markov game. Its original proof provided asymptotic guarantees and was for the tabular case. Recently, finite-sample guarantees have been provided using more modern RL techniques for the tabular case. Our work analyzes Nash Q-learning using linear function approximation -- a representation regime introduced when the state space is large or continuous -- and provides finite-sample guarantees that indicate its sample efficiency. We find that the obtained performance nearly matches an existing efficient result for single-agent RL under the same representation and has a polynomial gap when compared to the best-known result for the tabular case.
Submission history
From: Pedro Cisneros-Velarde [view email][v1] Wed, 1 Mar 2023 02:09:49 GMT (42kb)
Link back to: arXiv, form interface, contact.