Combinatorial Multi-armed Bandit with Probabilistically Triggered Arms: A Case with Bounded Regret.

Anil Ömer Saritaç Cem Tekin

Published in: CoRR (2017)

Keyphrases

multi armed bandits
multi armed bandit
multi armed bandit problems
bandit problems
reinforcement learning
regret bounds
active learning
online learning
decentralized decision making
lower bound
nearest neighbor