Papers
M.S. Abdulla and S. Bhatnagar, Reinforcement learning based algorithms for average cost Markov decision processes , Discrete Event Dynamical Systems, 23--52 (2007).
M.S. Abdulla and S. Bhatnagar, Solution of MDPs using simulation based value iteration , Proc. IFIP Conference on Artificial Intelligence Applications and Innovations, 2005.
S. Bhatnagar and M.S. Abdulla, A Reinforcement learning based algorithm for finite horizon Markov decision processes , Proc. IEEE Conference on Decision and Control, 2006.
M.S. Abdulla and S. Bhatnagar, SPSA Algorithms with Measurement Reuse , Proc. Winter Simulation Conference, 2006.
M.S. Abdulla and S. Bhatnagar, Solving MDPs using Two-timescale Simulated Annealing with Multiplicative Weights , Proc. American Control Conference, 2007.
M.S. Abdulla and S. Bhatnagar, Parametrized Actor-Critic Algorithms for Finite-Horizon MDPs , Proc. American Control Conference, 2007.
S. Bhatnagar and M.S. Abdulla, "Reinforcement learning based algorithms for finite horizon Markov decision processes", Submitted 2006.
M.S. Abdulla and S. Bhatnagar, Asynchronous stochastic approximation for network flow-control , Proc. IEEE Conference on Decision and Control, 2007.