N-Gram Induction Heads for In-Context RL: Improving Stability and Reducing Data Needs

4 November 2024

Andrei Polubarov

Igor Kiselev

Vladislav Kurenkov

Papers citing "N-Gram Induction Heads for In-Context RL: Improving Stability and Reducing Data Needs"

1 / 1 papers shown

Title
Yes, Q-learning Helps Offline In-Context RL Denis Tarasov Alexander Nikulin Ilya Zisman Albina Klepach Andrei Polubarov Nikita Lyubaykin Alexander Derevyagin Igor Kiselev Vladislav Kurenkov OffRL OnRL 76 0 0 24 Feb 2025