Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement LearningDownload PDFOpen Website

2018 (modified: 11 Nov 2022)ICML 2018Readers: Everyone
Abstract: We introduce SCAL, an algorithm designed to perform efficient exploration-exploration in any unknown weakly-communicating Markov Decision Process (MDP) for which an upper bound c on the span of the...
0 Replies

Loading