Reinforcement Learning For Decentralized Planning Under Uncertainty
Computing Sciences and Computer Engineering
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). Copyright © 2013, International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.
12th International Conference on Autonomous Agents and Multiagent Systems 2013, AAMAS 2013
(2013). Reinforcement Learning For Decentralized Planning Under Uncertainty. 12th International Conference on Autonomous Agents and Multiagent Systems 2013, AAMAS 2013, 2, 1439-1440.
Available at: https://aquila.usm.edu/fac_pubs/20422