@inproceedings{65364227b6cb483c80865e041b5a292c,
title = "Decentralized multi-agent reinforcement learning in average-reward dynamic DCOPs",
abstract = "Researchers have introduced the Dynamic Distributed Constraint Optimization Problem (Dynamic DCOP) formulation to model dynamically changing multi-agent coordination problems, where a dynamic DCOP is a sequence of (static canonical) DCOPs, each partially different from the DCOP preceding it. Existing work typically assumes that the problem in each time step is decoupled from the problems in other time steps, which might not hold in some applications. In this paper, we introduce a new model, called Markovian Dynamic DCOPs (MD-DCOPs), where a DCOP is a function of the value assignments in the preceding DCOP. We also introduce a distributed reinforcement learning algorithm that balances exploration and exploitation to solve MD-DCOPs in an online manner.",
keywords = "DCOP, Dynamic DCOP, MDP, Reinforcement Learning",
author = "Nguyen, \{Duc Thien\} and William Yeoh and Lau, \{Hoong Chuin\} and Shlomo Zilberstein and Chongjie Zhang",
note = "Publisher Copyright: Copyright {\textcopyright} 2014, International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.; 13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014 ; Conference date: 05-05-2014 Through 09-05-2014",
year = "2014",
language = "English",
series = "13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014",
publisher = "International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)",
pages = "1341--1342",
booktitle = "13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014",
}