Login / Signup

Dyna-Validator: A Model-based Reinforcement Learning Method with Validated Simulated Experiences.

Hengsheng ZhangJingchen LiZiming HeJinhui ZhuHaobin Shi
Published in: Int. J. Comput. Commun. Control (2023)
Keyphrases
  • objective function
  • pairwise
  • active learning
  • dynamic programming