Search papers, labs, and topics across Lattice.
FairPlay Team, CREST, ENSAE, Institut Polytechnique de Paris
2
0
3
Achieving optimal competitive ratios in prophet inequalities without relying on offline samples could revolutionize online learning strategies.
Even with noisy reward observations and unknown reward distributions, near-optimal online decision-making is possible using LCB thresholding, achieving competitive ratios of $1 - 1/e$ and $1/2$ in i.i.d. and non-i.i.d. settings, respectively.
