Logarithmic-Regret Quantum Learning Algorithms for Zero-Sum Games.
Minbo GaoZhengfeng JiTongyang LiQisheng WangPublished in: CoRR (2023)
Keyphrases
- learning algorithm
- worst case
- regret bounds
- machine learning algorithms
- lower bound
- learning problems
- online learning
- learning tasks
- machine learning
- opponent modeling
- learning rate
- online algorithms
- training data
- active learning
- reinforcement learning
- efficient learning
- supervised learning
- confidence bounds
- binary classification
- learning process
- optimal strategy
- quantum computing
- learning scheme
- game theory
- upper bound
- quantum computation
- membership queries
- loss function
- imperfect information
- decision tree learning
- decision trees
- expert advice
- weighted majority
- training samples
- labeled data
- upper confidence bound