Guided Data Augmentation for Offline Reinforcement Learning and Imitation Learning

[PDF] arxiv.org

HIPODE: Enhancing Offline Reinforcement Learning with High-Quality Synthetic Data from a Policy-Decoupled Approach

S Lian, Y Ma, J Liu, Y Zheng, Z Meng - arXiv preprint arXiv:2306.06329, 2023 - arxiv.org
Offline reinforcement learning (ORL) has gained attention as a means of training
reinforcement learning models using pre-collected static data. To address the issue of …
被引用次数：1 相关文章 所有 3 个版本