Reinforcement Learning on Bluue Whale

Reinforcement Learning on Bluue Whalehttps://bluuewhale.github.io/ko/tags/reinforcement-learning/Recent content in Reinforcement Learning on Bluue WhaleBluue Whalehttps://bluuewhale.github.io/images/profile.jpghttps://bluuewhale.github.io/images/profile.jpgHugo -- 0.152.2ko-krSat, 22 Aug 2026 22:21:36 +0900SIMA: A Generalist AI Agent for 3D Virtual Environmentshttps://bluuewhale.github.io/ko/posts/sima-generalist-ai-agent-3d-environments/Sun, 16 Nov 2025 09:20:13 +0900https://bluuewhale.github.io/ko/posts/sima-generalist-ai-agent-3d-environments/게임 엔진 API 대신 화면과 키보드/마우스만으로 여러 3D 게임을 플레이하는 딥마인드의 범용 에이전트 SIMA를, Behavior Cloning과 Classifier-Free Guidance를 중심으로 정리합니다.