Hyeong Soo Chang

Autom., 2006

Adversarial Multi-Armed Bandit Approach to Stochastic Optimization.

[BibT_eX]

[DOI]

Proceedings of the 45th IEEE Conference on Decision and Control, 2006

Reinforcement learning with supervision by combining multiple learnings and expert advices.

[BibT_eX]

[DOI]

Proceedings of the American Control Conference, 2006

2005

Evolutionary policy iteration for solving Markov decision processes.

[BibT_eX]

[DOI]

IEEE Trans. Autom. Control., 2005

Error bounds for finite step approximations for solving infinite horizon controlled Markov set-chains.

[BibT_eX]

[DOI]

IEEE Trans. Autom. Control., 2005

An Adaptive Sampling Algorithm for Solving Markov Decision Processes.

[BibT_eX]

[DOI]

Oper. Res., 2005

An ant system based multicasting in mobile ad hoc network.

[BibT_eX]

[DOI]

Se-young Lee

Proceedings of the IEEE Congress on Evolutionary Computation, 2005

Recursive Learning Automata for Control of Partially Observable Markov Decision Processes.

[BibT_eX]

[DOI]

Proceedings of the 44th IEEE IEEE Conference on Decision and Control and 8th European Control Conference Control, 2005

On Solving Controlled Markov Set-Chains via Multi-Policy Improvement.

[BibT_eX]

[DOI]

Proceedings of the 44th IEEE IEEE Conference on Decision and Control and 8th European Control Conference Control, 2005

2004

Multi-policy iteration with a distributed voting.

[BibT_eX]

[DOI]

Math. Methods Oper. Res., 2004

Parallel Rollout for Online Solution of Partially Observable Markov Decision Processes.

[BibT_eX]

[DOI]

Discret. Event Dyn. Syst., 2004

An adaptation of particle swarm optimization for Markov decision processes.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Systems, 2004

An ant system based exploration-exploitation for reinforcement learning.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Systems, 2004

Localization for a class of two-team zero-sum Markov games.

[BibT_eX]

[DOI]

Proceedings of the 43rd IEEE Conference on Decision and Control, 2004

An ant system approach to Markov decision processes.

[BibT_eX]

[DOI]

Proceedings of the 2004 American Control Conference, 2004

2003

Two-person zero-sum Markov games: receding horizon approach.

[BibT_eX]

[DOI]

IEEE Trans. Autom. Control., 2003

Multitime scale Markov decision processes.

[BibT_eX]

[DOI]

IEEE Trans. Autom. Control., 2003

Parallelizing Parallel Rollout Algorithm for Solving Markov Decision Processes.

[BibT_eX]

[DOI]

Seon Wook Kim

Proceedings of the OpenMP Shared Memory Parallel Programming, 2003

On the use of flow migration for handling short-term overloads.

[BibT_eX]

[DOI]

Proceedings of the Global Telecommunications Conference, 2003

An asymptotically efficient algorithm for finite horizon stochastic dynamic programming problems.

[BibT_eX]

[DOI]

Proceedings of the 42nd IEEE Conference on Decision and Control, 2003

A distributed algorithm for solving a class of multi-agent Markov decision problems.

[BibT_eX]

[DOI]

Proceedings of the 42nd IEEE Conference on Decision and Control, 2003

2002

Scheduling Multiclass Packet Streams to Minimize Weighted Loss.

[BibT_eX]

[DOI]

Queueing Syst. Theory Appl., 2002

Receding horizon approach to Markov games for infinite horizon discounted cost.

[BibT_eX]

[DOI]

Proceedings of the 41st IEEE Conference on Decision and Control, 2002

A model for multi-time scaled sequential decision making processes.

[BibT_eX]

[DOI]

Proceedings of the 41st IEEE Conference on Decision and Control, 2002

2000

A framework for simulation-based network control via hindsight optimization.

[BibT_eX]

[DOI]

Proceedings of the 39th IEEE Conference on Decision and Control, 2000

On-line Scheduling via Sampling.

[BibT_eX]

[DOI]