Partially decentralized reinforcement learning in finite, multi-agent Markov decision processes

Authors:
Omkar Tilak;Snehasis Mukhopadhyay
Affiliations:
(Correspd. E-mail: otilak@cs.iupui.edu) Department of Computer and Information Science, Indiana University-Purdue University, Indianapolis, IN, USA. E-mail: {otilak, smukhopa}@cs.iupui.edu;Department of Computer and Information Science, Indiana University-Purdue University, Indianapolis, IN, USA. E-mail: {otilak, smukhopa}@cs.iupui.edu
Venue:
AI Communications
Year:
2011

Citing 13
Cited 0

Learning optimal discriminant functions through a cooperative game of automata

IEEE Transactions on Systems, Man and Cybernetics
Learning automata: an introduction

Learning automata: an introduction
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Asynchronous Teams: Cooperation Schemes for Autonomous Agents

Journal of Heuristics
Solving multiconstraint assignment problems using learning automata

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Spectrum management of cognitive radio using multi-agent reinforcement learning

Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: Industry track
A novel multi-agent reinforcement learning approach for job scheduling in Grid computing

Future Generation Computer Systems
Decentralized and Partially Decentralized Reinforcement Learning for Distributed Combinatorial Optimization Problems

ICMLA '10 Proceedings of the 2010 Ninth International Conference on Machine Learning and Applications
Learning to compete, coordinate, and cooperate in repeated games using reinforcement learning

Machine Learning
Ant colony optimization

IEEE Computational Intelligence Magazine
A Comprehensive Survey of Multiagent Reinforcement Learning

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Varieties of learning automata: an overview

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Colonies of learning automata

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a novel, partially decentralized learning algorithm for the control of finite, multi-agent Markov Decision Process with unknown transition probabilities and reward values. One learning automaton is associated with each agent acting in a state and the automata acting within a state may communicate with each other. However, there is no communication between the automata present in different states, thus making the system partially decentralized. We propose novel algorithms so that the entire automata team converges to the policy that maximizes the long-term expected reward per step. Simulation results are presented to demonstrate the usefulness of the proposed algorithms.