Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization

no code implementations • 6 Nov 2023 • Kun Lei, Zhengmao He, Chenhao Lu, Kaizhe Hu, Yang Gao, Huazhe Xu

Owning to the alignment of objectives in two phases, the RL agent can transfer between offline and online learning seamlessly.

Reinforcement Learning (RL)