This talk will describe potential applications of some reinforcement learning algorithms originally developed for policy evaluation for certain Markov decision problems, for some Markov chain computations. Notably, computation of stationary expectations and stationary distributions will be considered. Connections with Monte Carlo and numerical schemes will be highlighted and some possible acceleration schemes will also be discussed.

  Vivek S. Borkar (M’95–SM’01–F’02) received the B.Tech. degree in electrical engineering from the Indian Institute of Technology Bombay, in 1976, the M.S. degree in systems and control from Case Western Reserve University, in 1977, and the Ph.D. degree in electrical engineering and computer science from University of California, Berkeley, in 1980.
  Professor Borkar has held positions at Tata Institute of Fundamental Research (TIFR) Center, Bangalore, Indian Institute of Science, Bangalore, and is currently with the School of Technology and Computer Science, TIFR, Mumbai. He has also held visiting positions at University of Twente, MIT, University of California, Berkeley, and University of Maryland, College Park. He has authored three books and over 100 archival publications, and is the recipient of several national and international honors, including the Fellowships of IEEE, various scientific academies in India, Homi Bhabha, and J. C. Bose Fellowships, S. S. Bhatnagar Award from the Government of India. His research interests are in theory, algorithms, and applications of stochastic optimization.