Approximations of the Restless Bandit Problem.
Steffen GrünewälderAzadeh KhaleghiPublished in: J. Mach. Learn. Res. (2019)
Keyphrases
- efficient computation
- optimal control
- random sampling
- markov chain
- bandit problems
- learning algorithm
- feature selection
- multi agent
- decentralized decision making
- conservation laws
- special case
- learning environment
- database
- database systems
- decision making
- computer vision
- artificial intelligence
- information retrieval
- databases