CDS Lecture Series

Wednesday, October 27, 1999, 3:00 p.m.

Vivek S. Borkar
School of Technology and Computer Science
Tata Institute of Fundamental Research
Bombay, India

Learning algorithms for MDPs: recent results

This talk will outline the basic philosophy behind reinforcement learning algorithms for Markov descision processes and sketch the techniques for their convergence analysis. With this backdrop, some recent extensions will be discussed.

Back to CDS Lecture Series
Back to Intelligent Servosystems Laboratory