학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2017.8,[iv. 30 p. :]
Reinforcement learning▼aMulti-armed Bandit problem▼aExploration exploitation tradeoff▼asequential decision problem▼aUnimodal condition; 강화학습▼a다중 슬롯머신 문제▼a탐사 이용 균형▼a순차적 결정 문제▼a단봉 상관관계
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.