Decentralized partially-observable Markov decision processes (Dec-POMDPs) are a powerful tool for modeling multi-agent planning and decision-making under uncertainty. Prevalent Dec-POMDP solution techniques require centralized computation given full knowledge of the underlying model. But in real world scenarios, model parameters may not be known a priori, or may be difficult to specify. We propose to address these limitations with distributed reinforcement learning (RL).
Paper
Full text
Reinforcement learning for decentralized planning under uncertainty
Semantic Scholar · Computer Science · 2013
Abstract
Decentralized partially-observable Markov decision processes (Dec-POMDPs) are a powerful tool for modeling multi-agent planning and decision-making under uncertainty. Prevalent Dec-POMDP solution techniques require centralized computation given full knowledge of the underlying model. But in real world scenarios, model parameters may not be known a priori, or may be difficult to specify. We propose to address these limitations with distributed reinforcement learning (RL).