Steering policies for controlled Markov chains under a recurrence condition
From MaRDI portal
Publication:4506874
DOI10.1109/9.780427zbMath0955.93061MaRDI QIDQ4506874
Armand M. Makowski, Dye-Jyun Ma
Publication date: 17 October 2000
Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1109/9.780427
adaptive control; Markov decision processes; sample path arguments; controlled Markov chains; recurrence condition; sample average costs
93E20: Optimal stochastic control
93E35: Stochastic learning and adaptive control
90C40: Markov and semi-Markov decision processes