Login / Signup

Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL.

Qinghua LiuGellért WeiszAndrás GyörgyChi JinCsaba Szepesvári
Published in: CoRR (2023)
Keyphrases
  • policy gradient
  • parametric optimization
  • optimal policy
  • actor critic
  • policy search
  • reinforcement learning
  • function approximation
  • control system
  • state space
  • optimization algorithm
  • markov decision processes