Information Gathering in Decentralized POMDPs by Policy Graph Improvement
arXiv: Artificial Intelligence, pp. 1143-1151, 2019.
We showed that if the reward function in a finite-horizon DecPOMDP is convex in the joint belief, the value function of any policy is convex in the joint belief
Decentralized policies for information gathering are required when multiple autonomous agents are deployed to collect data about a phenomenon of interest without the ability to communicate. Decentralized partially observable Markov decision processes (Dec-POMDPs) are a general, principled model well-suited for such decentralized multiagen...More
PPT (Upload PPT)