Indefinite-Horizon Reachability in Goal-DEC-POMDPs. Chatterjee, K. & Chmelík, M. In
Indefinite-Horizon Reachability in Goal-DEC-POMDPs [link]Paper  abstract   bibtex   
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.
@inproceedings {icaps16-33,
    track    = {​​Robotics Track},
    title    = {Indefinite-Horizon Reachability in Goal-DEC-POMDPs},
    url      = {http://www.aaai.org/ocs/index.php/ICAPS/ICAPS16/paper/view/12999},
    author   = {Krishnendu Chatterjee and  Martin Chmelík},
    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.},
    keywords = {formal methods for robot planning and control,planning and coordination methods for multiple robots}
}
Downloads: 0