no code implementations • 21 Dec 2019 • Arghyadip Roy, Vivek Borkar, Abhay Karandikar, Prasanna Chaporkar
To overcome the curses of dimensionality and modeling of Dynamic Programming (DP) methods to solve Markov Decision Process (MDP) problems, Reinforcement Learning (RL) methods are adopted in practice.
no code implementations • 28 Nov 2018 • Arghyadip Roy, Vivek Borkar, Abhay Karandikar, Prasanna Chaporkar
In this paper, we propose a new RL algorithm which utilizes the known threshold structure of the optimal policy while learning by reducing the feasible policy space.