method · first seen 16 Nov 2026
algorithm distillation
Training a sequence model on the learning histories of a reinforcement learning algorithm so it learns to adapt in context.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Algorithm Distillation for Safe In-Context Reinforcement LearningPapers · 16 Nov 2026 · Minjae Kwon, Amir Moeini, Shangtong Zhang, Lu Feng
Latest sources
- Algorithm Distillation for Safe In-Context Reinforcement LearningPapers · 16 Nov 2026 · Minjae Kwon, Amir Moeini, Shangtong Zhang, Lu Feng