Regret, stability, and fairness in matching markets with bandit learners.
Sarah Huiyi CenDevavrat ShahPublished in: CoRR (2021)
Keyphrases
- bandit problems
- matching algorithm
- learning environment
- e learning
- game theory
- multi armed bandit problems
- learning activities
- lower bound
- upper confidence bound
- learning experience
- learning process
- regret bounds
- online learning
- electronic commerce
- learning processes
- language learning
- multi armed bandit
- financial markets
- matching process
- learning materials
- learning systems
- graph matching
- learning resources
- learning strategies
- pattern matching