8 citations · 20 across the 11 of their papers we have counts for
Showing 2020Show all
2 papers · 1 filter
cs.LG2020
Stochastic Approximation with Markov Noise: Analysis and applications in reinforcement learning
Prasenjit Karmakar
We present for the first time an asymptotic convergence analysis of two time-scale stochastic approximation driven by "controlled" Markov noise. In particular, the faster and slowe…
math.PR2020
Customer-server population dynamics in heavy traffic
Rami Atar, Prasenjit Karmakar, David Lipshutz
We study a many-server queueing model with server vacations, where the population size dynamics of servers and customers are coupled: a server may leave for vacation only when no c…