Provably Breaking the Quadratic Error Compounding Barrier in Imitation Learning, Optimally

25 February 2021

Papers citing "Provably Breaking the Quadratic Error Compounding Barrier in Imitation Learning, Optimally"

2 / 2 papers shown

Title
Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining Licong Lin Yu Bai Song Mei OffRL 30 43 0 12 Oct 2023
Minimax Optimal Online Imitation Learning via Replay Estimation Gokul Swamy Nived Rajaraman Matt Peng Sanjiban Choudhury J. Andrew Bagnell Zhiwei Steven Wu Jiantao Jiao K. Ramchandran OffRL 24 18 0 30 May 2022