notesum.ai

Published at May 7

Warm-up Free Policy Optimization: Improved Regret in Linear Markov Decision Processes

NeurIPS

Released Date: May 7, 2024

Authors: Asaf Cassel¹, Aviv Rosenberg²

Aff.: ¹Tel Aviv University; ²Google Research

Arxiv: https://openreview.net/pdf/306830e11a9e3b0046b7c85d29e7cb963f283c26.pdf