{Q}-Learning Algorithms for Constrained Markov Decision Processes With Randomized Monotone Policies: Application to MIMO Transmission Control

DOI10.1109/TSP.2007.893228MaRDI QIDQ4564552zbMATH OpenWikidataFDO

Authors Dejan V. Djonin, Vikram Krishnamurthy

Publication date 12 June 2018

Published in IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/TSP.2007.893228

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Randomized algorithms (68W20) Markov and semi-Markov decision processes (90C40) Stochastic learning and adaptive control (93E35)

Cited in

(5)

• Constrained Markov decision processes with uncertain costs
• A reinforcement learning approach to call admission and call dropping control in links with variable capacity
• Langevin dynamics for adaptive inverse reinforcement learning of stochastic gradient algorithms
• Event-based optimization approach for solving stochastic decision problems with probabilistic constraint
• Sleeping experts and bandits approach to constrained Markov decision processes

This page was built for publication: ${Q}$-Learning Algorithms for Constrained Markov Decision Processes With Randomized Monotone Policies: Application to MIMO Transmission Control

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4564552)