Reinforcement Learning and Regret Bounds for Admission Control.
Lucas WeberAna BusicJiamin ZhuPublished in: CoRR (2024)
Keyphrases
- admission control
- reinforcement learning
- control policy
- regret bounds
- multi armed bandit
- end to end
- atm networks
- quality of service
- production system
- resource management
- machine learning
- state space
- web server
- online learning
- lower bound
- markov decision processes
- resource consumption
- optimal control
- long run
- linear regression
- optimal policy
- learning algorithm
- multi class
- dynamic programming
- multi agent
- bregman divergences
- database systems
- information retrieval