EE-Net is a contextual bandit algorithm that pairs an exploitation neural net with a separate exploration neural net and proves an instance-dependent Õ(√T) regret bound while beating linear and neural baselines on real data.
Provable regret bounds for deep online learning and control.arXiv preprint arXiv:2110.07807
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Neural Exploitation and Exploration of Contextual Bandits
EE-Net is a contextual bandit algorithm that pairs an exploitation neural net with a separate exploration neural net and proves an instance-dependent Õ(√T) regret bound while beating linear and neural baselines on real data.