Decentralized Multi-Armed Bandit Can Outperform Classic Upper Confidence Bound.

Jingxuan Zhu Ethan Mulle Christopher Salomon Smith Ji Liu

Published in: CoRR (2021)

Keyphrases

decentralized decision making
multi armed bandit
upper confidence bound
contextual bandit
multi agent
multi armed bandits
reinforcement learning
decision making
bandit problems
co occurrence
topic models
named entities