학위논문(박사) - 한국과학기술원 : 조천식녹색교통대학원, 2021.2,[ix, 72 p. :]
Multigoal reinforcement learning▼ahindsight experience replay▼asampling rate decay▼adelayed rewards▼abatch prioritization; 다중목표 강화학습▼ahindsight experience replay▼a샘플율 감쇠▼a희소 보상▼a배치 우선순위
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.