Regret of Queueing Bandits.
Subhashini KrishnasamyRajat SenRamesh JohariSanjay ShakkottaiPublished in: NIPS (2016)
Keyphrases
- regret bounds
- multi armed bandit problems
- multi armed bandit
- multi armed bandits
- online learning
- bandit problems
- steady state
- lower bound
- arrival rate
- linear regression
- priority scheduling
- queue length
- state dependent
- queueing theory
- loss function
- expert advice
- upper bound
- long run
- heavy traffic
- online convex optimization
- queueing model
- stochastic systems
- reinforcement learning
- confidence bounds
- least squares
- minimax regret
- dynamic programming
- multi agent
- scheduling policies
- queueing systems
- machine learning
- data sets
- interarrival and service times
- neural network