Login / Signup

Generalized exploration in policy search.

Herke van HoofDaniel TannebergJan Peters
Published in: Mach. Learn. (2017)
Keyphrases
  • policy search
  • reinforcement learning
  • dynamic programming
  • continuous action
  • continuous state
  • reinforcement learning algorithms
  • markov decision problems
  • reward function
  • policy gradient