Story

arxiv_cs_lg ยท Nov 16, 2026 ยท paper

Source brief

Algorithm Distillation for Safe In-Context Reinforcement Learning

arxiv.orgNov 16, 2026
original source linked

In brief

Safe in-context reinforcement learning (Safe ICRL) asks a policy with fixed parameters to improve on an unseen constrained task from its interaction history while aiming to keep its cost within a budget. Prior work st...

Feed lens
evaluation

Continue reading

Read the original at arxiv.org โ†’Open in live feedRead that dayโ€™s brief

Earlier in this thread 4 items