Indefinite-horizon reachability in Goal-DEC-POMDPs Conference Paper


Author(s): Chatterjee, Krishnendu; Chmelík, Martin
Title: Indefinite-horizon reachability in Goal-DEC-POMDPs
Affiliation IST Austria
Abstract: DEC-POMDPs extend POMDPs to a multi-agent setting, where several agents operate in an uncertain environment independently to achieve a joint objective. DEC-POMDPs have been studied with finite-horizon and infinite-horizon discounted-sum objectives, and there exist solvers both for exact and approximate solutions. In this work we consider Goal-DEC-POMDPs, where given a set of target states, the objective is to ensure that the target set is reached with minimal cost. We consider the indefinite-horizon (infinite-horizon with either discounted-sum, or undiscounted-sum, where absorbing goal states have zero-cost) problem. We present a new and novel method to solve the problem that extends methods for finite-horizon DEC-POMDPs and the RTDP-Bel approach for POMDPs. We present experimental results on several examples, and show that our approach presents promising results. Copyright
Keywords: reachability; Target state; Approximate solution; Finite horizons; Infinite horizons; Minimal cost; Multi-agent setting; Uncertain environments
Conference Title: ICAPS: International Conference on Automated Planning and Scheduling
Conference Dates: July 12-17, 2016
Conference Location: London, United Kingdom
ISBN: 978-157735731-5
Publisher: AAAI Press  
Date Published: 2016-01-01
Start Page: 88
End Page: 96
Sponsor: The research was partly supported by Austrian Science Fund (FWF) Grant No P23499-N23, FWF NFN Grant No S11407-N23 (RiSE), ERC Start grant (279307: Graph Games), and Microsoft faculty fellows award.
URL:
Notes: Technical Report at: https://repository.ist.ac.at/326/
Open access: yes (repository)
IST Austria Authors
  1. Martin Chmelik
    23 Chmelik
Related IST Austria Work