Search Results for author: Xiaoyue Sun

Found 1 papers, 0 papers with code

Delayed Rewards Calibration via Reward Empirical Sufficiency

no code implementations21 Feb 2021 Yixuan Liu, Hu Wang, Xiaowei Wang, Xiaoyue Sun, Liuyue Jiang, Minhui Xue

Therefore, a purify-trained classifier is designed to obtain the distribution and generate the calibrated rewards.

Cannot find the paper you are looking for? You can Submit a new open access paper.