Login / Signup

Comments on: "A policy improvement method for constrained average Markov decision processes" [ORL 35 (2007) 434-438].

Yasemin Serin
Published in: Oper. Res. Lett. (2009)
Keyphrases
  • markov decision processes
  • optimal policy
  • dynamic programming
  • policy iteration
  • reinforcement learning
  • data mining
  • convergence rate
  • infinite horizon
  • average cost
  • control policy
  • discounted reward