notesum.ai

Published at November 27

Concentration of Cumulative Reward in Markov Decision Processes

cs.LG
cs.SY
eess.SY
stat.ML

Released Date: November 27, 2024

Authors: Borna Sayedana1, Peter E. Caines1, Aditya Mahajan1

Aff.: 1Department of Electrical and Computer Engineering, McGill University, Montreal, QC, H3A 0E9, Canada

Arxiv: http://arxiv.org/abs/2411.18551v1