8 citations · 11 across the 7 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Robust Risk-Sensitive Reinforcement Learning from Corrupted Human Feedback
Xinyi Ni, Lifeng Lai
Reinforcement learning with human feedback (RLHF) learns from human comparisons, which can be corrupted or deliberately manipulated. This paper studies online risk-sensitive RLHF w…
stat.ML2026
Transformers Provably Implement In-Context Reinforcement Learning with Policy Improvement
Haodong Liang, Lifeng Lai
We investigate the ability of transformers to perform in-context reinforcement learning (ICRL), where a model must infer and execute learning algorithms from trajectory data withou…