Conference
Open access
Sep 2026
Mutual Information Guided Reinforcement Learning for Ambiguous Label Disambiguation
This work proposes a novel mutual information guided reinforcement learning framework for partial label disambiguation (MR-PLL), which is formulated as a sequential Markov decision process, where an agent dynamically discriminates whether to retain, modify, or abstain from correcting ambiguous labels.
Jin-Fu Fan, Jiangnan Li, Xiaohui Zhong et al.
· Proceedings of the Thirty-Fi... · 0 citations