Login / Signup
Scale-Free Adversarial Multi-Armed Bandit with Arbitrary Feedback Delays.
Jiatai Huang
Yan Dai
Longbo Huang
Published in:
CoRR (2021)
Keyphrases
</>
scale free
multi armed bandit
complex networks
multi armed bandits
small world
power law
scale free networks
small world networks
biological networks
small world properties
reinforcement learning
community structure
lower bound
active learning