Learning for Decentralized Control of Multiagent Systems in Large, Partially-Observable Stochastic Environments
AAAI, pp. 2523-2529, 2016.
Decentralized partially observable Markov decision processes (Dec-POMDPs) provide a general framework for multiagent sequential decision-making under uncertainty. Although Dec-POMDPs are typically intractable to solve for real-world problems, recent research on macro-actions (i.e., temporally-extended actions) has significantly increased ...More
PPT (Upload PPT)