Computer Science – Artificial Intelligence
Scientific paper
2011-10-31
Journal Of Artificial Intelligence Research, Volume 32, pages 289-353, 2008
Computer Science
Artificial Intelligence
Scientific paper
10.1613/jair.2447
Decision-theoretic planning is a popular approach to sequential decision making problems, because it treats uncertainty in sensing and acting in a principled way. In single-agent frameworks like MDPs and POMDPs, planning can be carried out by resorting to Q-value functions: an optimal Q-value function Q* is computed in a recursive manner by dynamic programming, and then an optimal policy is extracted from Q*. In this paper we study whether similar Q-value functions can be defined for decentralized POMDP models (Dec-POMDPs), and how policies can be extracted from such value functions. We define two forms of the optimal Q-value function for Dec-POMDPs: one that gives a normative description as the Q-value function of an optimal pure joint policy and another one that is sequentially rational and thus gives a recipe for computation. This computation, however, is infeasible for all but the smallest problems. Therefore, we analyze various approximate Q-value functions that allow for efficient computation. We describe how they relate, and we prove that they all provide an upper bound to the optimal Q-value function Q*. Finally, unifying some previous approaches for solving Dec-POMDPs, we describe a family of algorithms for extracting policies from such Q-value functions, and perform an experimental evaluation on existing test problems, including a new firefighting benchmark problem.
Oliehoek Frans A.
Spaan Matthijs T. J.
Vlassis Nikos
No associations
LandOfFree
Optimal and Approximate Q-value Functions for Decentralized POMDPs does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Optimal and Approximate Q-value Functions for Decentralized POMDPs, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Optimal and Approximate Q-value Functions for Decentralized POMDPs will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-466831