Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining

arXiv2310.08566MaRDI QIDQ6454951

Author name not available (Why is that?)

Publication date: 12 October 2023

Has companion code repository: https://github.com/licong-lin/in-context-rl

This page was built for publication: Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6454951)