Login / Signup

Asymptotics for renewal-reward processes with retrospective reward structure.

Attila Csenki
Published in: Oper. Res. Lett. (2000)
Keyphrases
  • reinforcement learning
  • markov chain
  • long run
  • bandit problems
  • data mining
  • structural properties
  • databases
  • multiscale
  • expert systems
  • xml documents
  • hidden markov models
  • reward function