all AI news
Optimistic Thompson Sampling for No-Regret Learning in Unknown Games
Feb. 16, 2024, 5:41 a.m. | Yingru Li, Liangqi Liu, Wenqiang Pi, Hao Liang, Zhi-Quan Luo
cs.LG updates on arXiv.org arxiv.org
Abstract: Many real-world problems involving multiple decision-makers can be modeled as an unknown game characterized by partial observations. Addressing the challenges posed by partial information and the curse of multi-agency, we developed Thompson sampling-type algorithms, leveraging information about opponent's action and reward structures. Our approach significantly reduces experimental budgets, achieving a more than tenfold reduction compared to baseline algorithms in practical applications like traffic routing and radar sensing. We demonstrate that, under certain assumptions about the …
abstract agency algorithms arxiv challenges cs.ai cs.lg decision game games information makers multiple sampling stat.ml type world
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US