Skip to content
conftrace_
2024 ICML ICML 2024

Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Yu Luo, Tianying Ji, Fuchun Sun, Jianwei Zhang, Huazhe Xu, Xianyuan Zhan

Topics

Reinforcement Learning > Methods > Offline RL Reinforcement Learning > Methods > Policy Learning Reinforcement Learning > Applications > Robotics

Keywords

sample efficiency asymptotic performance value comparison adaptive constraint offline-boosted actor-critic online replay buffer
Download PDF