AI RESEARCH
Quantile Q-Learning: Revisiting Offline Extreme Q-Learning with Quantile Regression
arXiv CS.LG
•
ArXi:2511.11973v2 Announce Type: replace Offline reinforcement learning (RL) enables policy learning from fixed datasets without further environment interaction, making it particularly valuable in high-risk or costly domains. Extreme $Q$-Learning (XQL) is a recent offline RL method that models Bellman errors using the Extreme Value Theorem, yielding strong empirical performance. However, XQL and its stabilized variant MXQL suffer from notable limitations: both require extensive hyperparameter tuning specific to each dataset and domain, and also exhibit instability during