Cascaded Gaps: Towards Logarithmic Regret for Risk-Sensitive Reinforcement LearningDownload PDFOpen Website

2022 (modified: 16 Apr 2023)ICML 2022Readers: Everyone
Abstract: In this paper, we study gap-dependent regret guarantees for risk-sensitive reinforcement learning based on the entropic risk measure. We propose a novel definition of sub-optimality gaps, which we ...
0 Replies

Loading