Expert-guided imitation learning for energy management: Evaluating GAIL's performance in building control applications
Abstract The use of Deep Reinforcement Learning (DRL) in building energy management is
often hampered by data efficiency and computational challenges. The long training time …
often hampered by data efficiency and computational challenges. The long training time …
A scalable approach for real-world implementation of deep reinforcement learning controllers in buildings based on online transfer learning: The HiLo case study
Abstract In recent years, Transfer Learning (TL) has emerged as a promising solution to
scale Deep Reinforcement Learning (DRL) controllers for building energy management …
scale Deep Reinforcement Learning (DRL) controllers for building energy management …
Explorative imitation learning: A path signature approach for continuous environments
Some imitation learning methods combine behavioural cloning with self-supervision to infer
actions from state pairs. However, most rely on a large number of expert trajectories to …
actions from state pairs. However, most rely on a large number of expert trajectories to …
저편향· 고분산된보편적데이터를이용한효율적인오프라인강화학습방법
권은주， 김현석 - 디지털콘텐츠학회논문지, 2024 - dbpia.co.kr
대규모 언어 모델 (Large Language Model) 기반 Robotic Transformer 활용으로 로봇은 복잡한
시퀀스 문제도 스스로 해결할 수 있게 되었으나, 여전히 단위 행동은 사전에 획득된 고품질 …
시퀀스 문제도 스스로 해결할 수 있게 되었으나, 여전히 단위 행동은 사전에 획득된 고품질 …