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

D. V. Djonin and V. Krishnamurthy، نويسنده ,

روزنامه با شماره پیاپی سال 2007

12

2170

2181

Delay constraints , learning , randomized policies , Supermodularity , transmission scheduling , V-BLAST. , monotone policies , reinforcement learning , Constrained Markov decision process (CMDP)

IEEE TRANSACTIONS ON SIGNAL PROCESSING

2007

IEEE TRANSACTIONS ON SIGNAL PROCESSING

389883