Bayesian role discovery for multi-agent reinforcement learning

Authors:
Aaron Wilson;Alan Fern;Prasad Tadepalli
Affiliations:
Oregon State University;Oregon State University;Oregon State University
Venue:
Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume 1 - Volume 1
Year:
2010

Citing 4
Cited 2

Bayesian Q-learning

AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
On being a teammate: experiences acquired in the design of RoboCup teams

Proceedings of the third annual conference on Autonomous Agents
A Bayesian Framework for Reinforcement Learning

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Importance sampling for reinforcement learning with multiple objectives

Importance sampling for reinforcement learning with multiple objectives

Location-based reasoning about complex multi-agent behavior

Journal of Artificial Intelligence Research
Modeling of route planning system based on Q value-based dynamic programming with multi-agent reinforcement learning algorithms

Engineering Applications of Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we develop a Bayesian policy search approach for Multi-Agent RL (MARL), which is model-free and allows for priors on policy parameters. We present a novel optimization algorithm based on hybrid MCMC, which leverages both the prior and gradient information estimated from trajectories. Our experiments demonstrate the automatic discovery of roles through reinforcement learning in a real-time strategy game.