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

researchr

You are not signed in
Sign in
Sign up

Dejan V. Djonin, Vikram Krishnamurthy. Q-Learning Algorithms for Constrained Markov Decision Processes With Randomized Monotone Policies: Application to MIMO Transmission Control. IEEE Transactions on Signal Processing, 55(5-2):2170-2181, 2007. [doi]

Abstract is missing.

runs on WebDSL