conftrace_

exp4 algorithm

2 papers

Explore in graph

Also known as

EXP4

Co-occurring keywords · papers mentioning both

regret bound (2) online learning (2) mediator feedback (1) policy set capacity (1) information capacity (1) policy set (1) policy class (1) supervised learning guarantee (1) contextual bandit (1) multi-armed bandit (1)

Papers

Information Capacity Regret Bounds for Bandits with Mediator Feedback JMLR 2024 Contextual Bandit Algorithms with Supervised Learning Guarantees AISTATS 2011