Login / Signup

An inverse reinforcement learning algorithm for semi-Markov decision processes.

Chuanfang TanYanjie LiYuhu Cheng
Published in: SSCI (2017)
Keyphrases
  • semi markov decision processes
  • markov decision processes
  • average reward
  • long run
  • optimal policy
  • monte carlo
  • reinforcement learning
  • lower bound
  • policy iteration