9 papers
Transformation of Adaptive Multistage Sampling for Solving Finite-Horizon Markov Decision Processes with Unknown Model
Hyeong Soo Chang
This work provides a learning approach to solving finite-horizon Markov decision processes (MDPs) when the underlying model of a given finite MDP is unknown to the decision maker.…
On the Convergence Rate of MCTS for the Optimal Value Estimation in Markov Decision Processes
Hyeong Soo Chang
A recent theoretical analysis of a Monte-Carlo tree search (MCTS) method properly modified from the ``upper confidence bound applied to trees" (UCT) algorithm established a surpris…
Top Feasible-Arm Subset Identification in Constrained Multi-Armed Bandit with Limited Budget
Hyeong Soo Chang
We present an algorithm, "constrained successive accept or reject (CSAR)," for the problem of identifying the subset of top feasible-arms from a given finite set of arms with the l…
Approximate Constrained Discounted Dynamic Programming with Uniform Feasibility and Optimality
Hyeong Soo Chang
We consider a dynamic programming (DP) approach to approximately solving an infinite-horizon constrained Markov decision process (CMDP) problem with a fixed initial-state for the e…
On Supervised On-line Rolling-Horizon Control for Infinite-Horizon Discounted Markov Decision Processes
Hyeong Soo Chang
This note re-visits the rolling-horizon control approach to the problem of a Markov decision process (MDP) with infinite-horizon discounted expected reward criterion. Distinguished…
On-line Policy Iteration with Policy Switching for Markov Decision Processes
Hyeong Soo Chang
Motivated from Bertsekas' recent study on policy iteration (PI) for solving the problems of infinite-horizon discounted Markov decision processes (MDPs) in an on-line setting, we d…