[논문 리뷰] Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learning

논문 정보

제목: Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learning

저자: Franki Nguimatsia Tiofack, Théotime Le Hellard, Fabian Schramm, Nicolas Perrin-Gilbert, Justin Carpentier

학회: ICLR 2026 Poster

링크: https://arxiv.org/abs/2512.03973