Operations Research, Systems Engineering and Industrial Engineering Commons^™

Two Essays On Dynamic Programming And Reinforcement Learning, Shuva Ghosh

Doctoral Dissertations

"The semi-Markov decision process (SMDP) is a variant of the Markov decision process (MOP). This dissertation work focuses on the application of SMDPs to disaster response management and to maintenance management. Average and discounted reward are two popular performance metrics for MDPs/SMDPs. While both dynamic programming (DP) methods, i.e., value iteration and policy iteration, are commonly used to solve MDPs/SMDPs, value iteration is easier to apply than policy iteration. The existing value iteration algorithms for average reward SMDPs have some noteworthy limitations, which are sought to be overcome in this work. Reinforcement learning (RL) techniques, which are also studied in …