5 citations · 10 across the 5 of their papers we have counts for
Showing 2015Show all
2 papers · 1 filter
cs.LG2015
A constrained optimization perspective on actor critic algorithms and application to network routing
Prashanth L. A., H. L. Prasad, Shalabh Bhatnagar +1
We propose a novel actor-critic algorithm with guaranteed convergence to an optimal policy for a discounted reward Markov decision process. The actor incorporates a descent directi…
cs.LG2015★ 4 cited
A Study of Gradient Descent Schemes for General-Sum Stochastic Games
H. L. Prasad, Shalabh Bhatnagar
Zero-sum stochastic games are easy to solve as they can be cast as simple Markov decision processes. This is however not the case with general-sum stochastic games. A fairly genera…