Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Revisiting Overestimation Bias Problem of Q-learning: Settling Large Discrete Action Space via Action Intersection
Pu Li, Tao Tan, Hong Xie +2
This paper considers the overestimation bias problem of Q-learning in the setting of a large action space, for the purpose of relieving the bottleneck of existing methods. We find…
cs.LG2026
Fairness Begins with State: Purifying Latent Preferences for Hierarchical Reinforcement Learning in Interactive Recommendation
Yun Lu, Xiaoyu Shi, Hong Xie +2
Interactive recommender systems (IRS) are increasingly optimized with Reinforcement Learning (RL) to capture the sequential nature of user-system dynamics. However, existing fairne…