all AI news
Corruption-Robust Offline Two-Player Zero-Sum Markov Games
March 14, 2024, 4:42 a.m. | Andi Nika, Debmalya Mandal, Adish Singla, Goran Radanovi\'c
cs.LG updates on arXiv.org arxiv.org
Abstract: We study data corruption robustness in offline two-player zero-sum Markov games. Given a dataset of realized trajectories of two players, an adversary is allowed to modify an $\epsilon$-fraction of it. The learner's goal is to identify an approximate Nash Equilibrium policy pair from the corrupted data. We consider this problem in linear Markov games under different degrees of data coverage and corruption. We start by providing an information-theoretic lower bound on the suboptimality gap of …
abstract arxiv corrupted data corruption cs.gt cs.lg data dataset epsilon equilibrium games identify markov nash equilibrium offline policy robust robustness study type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US