Hyeong Soo Chang

60 papers B 2C 2Journal 40Unranked 16
YearRankTypeTitle / Venue / Authors
2025 J jnl
Approximate Constrained Discounted Dynamic Programming With Uniform Feasibility and Optimality.
IEEE Trans. Autom. Control.
Hyeong Soo Chang
2025 J jnl
On the Convergence Rate of MCTS for the Optimal Value Estimation in Markov Decision Processes.
IEEE Trans. Autom. Control.
Hyeong Soo Chang
2024 J jnl
On Supervised Online Rolling-Horizon Control for Infinite-Horizon Discounted Markov Decision Processes.
IEEE Trans. Autom. Control.
Hyeong Soo Chang
2021 J jnl
An index-based deterministic convergent optimal algorithm for constrained multi-armed bandit problems.
Autom.
Hyeong Soo Chang
2020 J jnl
An Index-based Deterministic Asymptotically Optimal Algorithm for Constrained Multi-armed Bandit Problems.
CoRR
Hyeong Soo Chang
2020 J jnl
An asymptotically optimal strategy for constrained multi-armed bandit problems.
Math. Methods Oper. Res.
Hyeong Soo Chang
2018 J jnl
An Asymptotically Optimal Strategy for Constrained Multi-armed Bandit Problems.
CoRR
Hyeong Soo Chang
2017 J jnl
Value set iteration for two-person zero-sum Markov games.
Autom.
Hyeong Soo Chang
2016 J jnl
Sleeping experts and bandits approach to constrained Markov decision processes.
Autom.
Hyeong Soo Chang
2015 J jnl
Random search for constrained Markov decision processes with multi-policy improvement.
Autom.
Hyeong Soo Chang
2014 J jnl
An exact iterative search algorithm for constrained Markov decision processes.
Autom.
Hyeong Soo Chang
2014 J jnl
Value set iteration for Markov decision processes.
Autom.
Hyeong Soo Chang
2013 J jnl
On functional equations for Kth best policies in Markov decision processes.
Autom.
Hyeong Soo Chang
2013 J jnl
Policy set iteration for Markov decision processes.
Autom.
Hyeong Soo Chang
2012 J jnl
A Stochastic Approximation Framework for a Class of Randomized Optimization Algorithms.
IEEE Trans. Autom. Control.
Jiaqiao Hu, Ping Hu, Hyeong Soo Chang
2012 J jnl
A policy iteration heuristic for constrained discounted controlled Markov Chains.
Optim. Lett.
Hyeong Soo Chang
2012 J jnl
Approximate stochastic annealing for online control of infinite horizon Markov decision processes.
Autom.
Jiaqiao Hu, Hyeong Soo Chang
2012 J jnl
On the Probability of Correct Selection in Ordinal Comparison over Dynamic Networks.
J. Optim. Theory Appl.
Hyeong Soo Chang, Jiaqiao Hu
2011 J jnl
Dynamic sample budget allocation in model-based optimization.
J. Glob. Optim.
Jiaqiao Hu, Hyeong Soo Chang, Michael C. Fu, Steven I. Marcus
2010 J jnl
Adaptive Adversarial Multi-Armed Bandit Approach to Two-Person Zero-Sum Markov Games.
IEEE Trans. Autom. Control.
Hyeong Soo Chang, Jiaqiao Hu, Michael C. Fu, Steven I. Marcus
2010 — conf
An Approximate Stochastic Annealing algorithm for finite horizon Markov decision processes.
CDC
Jiaqiao Hu, Hyeong Soo Chang
2009 J jnl
Decentralized Learning in Finite Markov Chains: Revisited.
IEEE Trans. Autom. Control.
Hyeong Soo Chang
2008 — conf
A population-based cross-entropy method with dynamic sample allocation.
CDC
Jiaqiao Hu, Hyeong Soo Chang
2008 J jnl
Converging Coevolutionary Algorithm for Two-Person Zero-Sum Discounted Markov Games With Perfect Information.
IEEE Trans. Autom. Control.
Hyeong Soo Chang
2008 J jnl
Finite-Step Approximation Error Bounds for Solving Average-Reward-Controlled Markov Set-Chains.
IEEE Trans. Autom. Control.
Hyeong Soo Chang
2007 J jnl
A policy improvement method for constrained average Markov decision processes.
Oper. Res. Lett.
Hyeong Soo Chang
2007 J jnl
A survey of some simulation-based algorithms for Markov decision processes.
Commun. Inf. Syst.
Hyeong Soo Chang, Michael C. Fu, Jiaqiao Hu, Steven I. Marcus
2007 — conf
Adversarial multi-armed bandit approach to two-person zero-sum Markov games.
CDC
Hyeong Soo Chang, Michael C. Fu, Steven I. Marcus
2007 J jnl
An Asymptotically Efficient Simulation-Based Algorithm for Finite Horizon Stochastic Dynamic Programming.
IEEE Trans. Autom. Control.
Hyeong Soo Chang, Michael C. Fu, Jiaqiao Hu, Steven I. Marcus
2007 J jnl
Recursive Learning Automata Approach to Markov Decision Processes.
IEEE Trans. Autom. Control.
Hyeong Soo Chang, Michael C. Fu, Jiaqiao Hu, Steven I. Marcus
2007 J jnl
Solving Controlled Markov Set-Chains With Discounting via Multipolicy Improvement.
IEEE Trans. Autom. Control.
Hyeong Soo Chang, Edwin K. P. Chong
2006 J jnl
A Policy Improvement Method in Constrained Stochastic Dynamic Programming.
IEEE Trans. Autom. Control.
Hyeong Soo Chang
2006 J jnl
Advances in Dynamic Games, Applications to Economics, Finance, Optimization, and Stochastic Control: A.S. Nowak, K. Szajowski (Eds.); Birkhauser, Boston, 2005, ISBN 0-8176-4362-1.
Autom.
Hyeong Soo Chang
2006 — conf
Adversarial Multi-Armed Bandit Approach to Stochastic Optimization.
CDC
Hyeong Soo Chang, Michael C. Fu, Steven I. Marcus
2006 J jnl
Converging Marriage in Honey-Bees Optimization and Application to Stochastic Dynamic Programming.
J. Glob. Optim.
Hyeong Soo Chang
2006 J jnl
Perfect information two-person zero-sum markov games with imprecise transition probabilities.
Math. Methods Oper. Res.
Hyeong Soo Chang
2006 C conf
Reinforcement learning with supervision by combining multiple learnings and expert advices.
ACC
Hyeong Soo Chang
2005 J jnl
An Adaptive Sampling Algorithm for Solving Markov Decision Processes.
Oper. Res.
Hyeong Soo Chang, Michael C. Fu, Jiaqiao Hu, Steven I. Marcus
2005 B conf
An ant system based multicasting in mobile ad hoc network.
Congress on Evolutionary Computation
Se-young Lee, Hyeong Soo Chang
2005 J jnl
Error bounds for finite step approximations for solving infinite horizon controlled Markov set-chains.
IEEE Trans. Autom. Control.
Hyeong Soo Chang
2005 J jnl
Evolutionary policy iteration for solving Markov decision processes.
IEEE Trans. Autom. Control.
Hyeong Soo Chang, Hong-Gi Lee, Michael C. Fu, Steven I. Marcus
2005 — conf
On Solving Controlled Markov Set-Chains via Multi-Policy Improvement.
CDC/ECC
Hyeong Soo Chang, Edwin K. P. Chong
2005 — conf
Recursive Learning Automata for Control of Partially Observable Markov Decision Processes.
CDC/ECC
Hyeong Soo Chang, Michael C. Fu, Steven I. Marcus
2004 — conf
An adaptation of particle swarm optimization for Markov decision processes.
SMC (2)
Hyeong Soo Chang
2004 C conf
An ant system approach to Markov decision processes.
ACC
Hyeong Soo Chang, Walter J. Gutjahr, Jihoon Yang, Sungyong Park
2004 — conf
An ant system based exploration-exploitation for reinforcement learning.
SMC (4)
Hyeong Soo Chang
2004 — conf
Localization for a class of two-team zero-sum Markov games.
CDC
Hyeong Soo Chang, Michael C. Fu
2004 J jnl
Multi-policy iteration with a distributed voting.
Math. Methods Oper. Res.
Hyeong Soo Chang
2004 J jnl
Parallel Rollout for Online Solution of Partially Observable Markov Decision Processes.
Discret. Event Dyn. Syst.
Hyeong Soo Chang, Robert Givan, Edwin K. P. Chong
2003 — conf
A distributed algorithm for solving a class of multi-agent Markov decision problems.
CDC
Hyeong Soo Chang, Michael C. Fu
2003 — conf
An asymptotically efficient algorithm for finite horizon stochastic dynamic programming problems.
CDC
Hyeong Soo Chang, Michael C. Fu, Steven I. Marcus
2003 J jnl
Multitime scale Markov decision processes.
IEEE Trans. Autom. Control.
Hyeong Soo Chang, Pedram Jaefari Fard, Steven I. Marcus, Mark A. Shayman
2003 B conf
On the use of flow migration for handling short-term overloads.
GLOBECOM
Kuo-Tung Kuo, Surapich Phuvoravan, Bobby Bhattacharjee, Richard J. La, Mark A. Shayman, Hyeong Soo Chang
2003 — conf
Parallelizing Parallel Rollout Algorithm for Solving Markov Decision Processes.
WOMPAT
Seon Wook Kim, Hyeong Soo Chang
2003 J jnl
Two-person zero-sum Markov games: receding horizon approach.
IEEE Trans. Autom. Control.
Hyeong Soo Chang, Steven I. Marcus
2002 — conf
A model for multi-time scaled sequential decision making processes.
CDC
Hyeong Soo Chang, Pedram Jaefari Fard, Steven I. Marcus, Mark A. Shayman
2002 — conf
Receding horizon approach to Markov games for infinite horizon discounted cost.
CDC
Hyeong Soo Chang, Steven I. Marcus
2002 J jnl
Scheduling Multiclass Packet Streams to Minimize Weighted Loss.
Queueing Syst. Theory Appl.
Robert Givan, Edwin K. P. Chong, Hyeong Soo Chang
2000 — conf
A framework for simulation-based network control via hindsight optimization.
CDC
Edwin K. P. Chong, Robert Givan, Hyeong Soo Chang
2000 — conf
On-line Scheduling via Sampling.
AIPS
Hyeong Soo Chang, Robert Givan, Edwin K. P. Chong