Rectified Pessimistic-Optimistic Learning for Stochastic Continuum-armed Bandit with Constraints.

Hengquan Guo Qi Zhu Xin Liu

Published in: CoRR (2022)

Keyphrases

supervised learning
learning process
online learning
learning algorithm
learning systems

reinforcement learning
unsupervised learning
knowledge acquisition
constrained optimization

data sets
learning tasks
constraint satisfaction
graphical models

decision trees
e learning
genetic algorithm
machine learning