2 papers
cs.LG2023
Beyond Reward: Offline Preference-guided Policy Optimization
Yachen Kang, Diyuan Shi, Jinxin Liu +2
This study focuses on the topic of offline preference-based reinforcement learning (PbRL), a variant of conventional reinforcement learning that dispenses with the need for online…
physics.app-ph2021
A scatter correction method for Multi-MeV Flash Radiography
Qinggang Jia, Peng-Cheng Mao, Yang-Bo +4
Multi-MeV flash radiography is often used as the primary diagnostic technique for high energy and density (HED) physics experiments. Primary X-ray which is attenuated by the object…