Continuous Time Associative Bandit Problems.
András GyörgyLevente KocsisIvett SzabóCsaba SzepesváriPublished in: IJCAI (2007)
Keyphrases
- bandit problems
- multi armed bandits
- decision problems
- markov chain
- markov processes
- exploration exploitation
- dynamical systems
- stochastic processes
- associative memory
- iterative learning control
- state space
- optimal control
- decentralized decision making
- expected utility
- multi armed bandit problems
- spreading activation
- cooperative
- worst case
- special case