A reinforcement learning algorithm for restless bandits
- Resource Type
- Conference
- Authors
- Borkar, Vivek S.; Chadha, Karan
- Source
- 2018 Indian Control Conference (ICC) Indian Control Conference (ICC). 2018. :89-94 Jan, 2018
- Subject
- Aerospace
Bioengineering
Robotics and Control Systems
Signal Processing and Analysis
Silicon
Indexes
Learning (artificial intelligence)
Approximation algorithms
Function approximation
Poisson equations
Markov processes
- Language
We propose and analyze a reinforcement learning algorithm for learning Whittle index for a class of indexable restless bandits based on linear function approximation and illustrate its use using as an example a restless bandit problem arising in scheduling of web crawlers for ephemeral content.