Multiagent reinforcement learning: algorithm converging to Nash equilibrium in general-sum discounted stochastic games

Authors:
Natalia Akchurina
Affiliations:
University of Paderborn, Paderborn, Germany
Venue:
Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems - Volume 2
Year:
2009

Citing 5
Cited 4

Competitive Markov decision processes

Competitive Markov decision processes
The dynamics of reinforcement learning in cooperative multiagent systems

AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
Multiagent learning using a variable learning rate

Artificial Intelligence
Friend-or-Foe Q-learning in General-Sum Games

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm

ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning

Social conformity and its convergence for reinforcement learning

MATES'10 Proceedings of the 8th German conference on Multiagent system technologies
Social welfare for automatic innovation

MATES'11 Proceedings of the 9th German conference on Multiagent system technologies
A general framework for interacting bayes-optimally with self-interested agents using arbitrary parametric model and model prior

IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
An actor-critic algorithm for multi-agent learning in queue-based stochastic games

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper introduces a multiagent reinforcement learning algorithm that converges with a given accuracy to stationary Nash equilibria in general-sum discounted stochastic games. Under some assumptions we formally prove its convergence to Nash equilibrium in self-play. We claim that it is the first algorithm that converges to stationary Nash equilibrium in the general case.