Zobrazeno 1 - 10
of 142
pro vyhledávání: '"Hyeong Soo Chang"'
Autor:
Hyeong Soo Chang, Sanghee Choe
Publikováno v:
Journal of Control Science and Engineering, Vol 2015 (2015)
This brief paper provides a simple algorithm that selects a strategy at each time in a given set of multiple strategies for stochastic multiarmed bandit problems, thereby playing the arm by the chosen strategy at each time. The algorithm follows the
Externí odkaz:
https://doaj.org/article/59737aa0f04f4adab501f9513cd682e9
Autor:
Hyeong Soo Chang
Publikováno v:
Automatica. 76:61-64
We present a novel exact algorithm called “value set iteration” (VSI) for solving two-person zero-sum Markov games (MGs) as a generalization of value iteration (VI) and as a general framework of combining multiple solution methods. We introduce a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b7e815601110ef01aa54f07faea69d24
https://doi.org/10.1016/j.automatica.2016.10.010
https://doi.org/10.1016/j.automatica.2016.10.010
Autor:
Sanghee Choi, Hyeong Soo Chang
Publikováno v:
Journal of KIISE. 44:63-70
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6a1a85b615a3b59eb55458827d4c63c3
https://doi.org/10.5626/jok.2017.44.1.63
https://doi.org/10.5626/jok.2017.44.1.63
Autor:
Hyeong Soo Chang
This note considers the model of “constrained multi-armed bandit” (CMAB) that generalizes that of the classical stochastic MAB by adding a feasibility constraint for each action. The feasibility is in fact another (conflicting) objective that sho
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::87a466dd383b43a1283c04b0308bb1f6
http://arxiv.org/abs/1805.01237
http://arxiv.org/abs/1805.01237
Autor:
Hyeong Soo Chang
Publikováno v:
Automatica. 58:127-130
This communique first presents a novel multi-policy improvement method which generates a feasible policy at least as good as any policy in a given set of feasible policies in finite constrained Markov decision processes (CMDPs). A random search algor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4aebcc125aa57160b450b99ff02b3594
https://doi.org/10.1016/j.automatica.2015.05.016
https://doi.org/10.1016/j.automatica.2015.05.016
Autor:
Hyeong Soo Chang
Publikováno v:
Automatica. 50:1940-1943
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6e337ba459cb8953a3f9511851c7e733
https://doi.org/10.1016/j.automatica.2014.05.009
https://doi.org/10.1016/j.automatica.2014.05.009
Autor:
Hyeong Soo Chang
Publikováno v:
Automatica. 50:1531-1534
This communique provides an exact iterative search algorithm for the NP-hard problem of obtaining an optimal feasible stationary Markovian pure policy that achieves the maximum value averaged over an initial state distribution in finite constrained M
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1c66ddcc531b5bede286b372a058fd9b
https://doi.org/10.1016/j.automatica.2014.03.020
https://doi.org/10.1016/j.automatica.2014.03.020
Autor:
Hyeong Soo Chang
Publikováno v:
Optimization. 64:1647-1655
Motivated by the work of Homem-De-Mello on modifying pure random search (PRS) into a convergent sample-based PRS for stochastic optimization, this paper considers two general methods of converting any given population-based algorithm into a convergen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c1e8f951580122a6ef8310dd390121f4
https://doi.org/10.1080/02331934.2014.883511
https://doi.org/10.1080/02331934.2014.883511
Autor:
Hyeong Soo Chang
Publikováno v:
Game Theory. 2013:1-5
We provide a necessary condition that a constrained Nash-equilibrium (CNE) policy pair satisfies in two-person zero-sum constrained stochastic discounted-payoff games and discuss a general method of approximating CNE based on the condition.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8771b2e9b4096d666bd57357cbe0edbb
https://doi.org/10.1155/2013/290427
https://doi.org/10.1155/2013/290427
Autor:
Hyeong Soo Chang
Publikováno v:
Automatica. 49:297-300
This paper revisits the problem of finding the values of Kth best policies for finite-horizon finite Markov decision processes. The recursive dynamic-programming (DP) equations established by Bellman and Kalaba for non-deterministic MDPs with zero-co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ba7436502eb3683f1fe5a41758e16563
https://doi.org/10.1016/j.automatica.2012.09.016
https://doi.org/10.1016/j.automatica.2012.09.016