Login / Signup

Policy derivation methods for critic-only reinforcement learning in continuous spaces.

Eduard AlibekovJirí KubalíkRobert Babuska
Published in: Eng. Appl. Artif. Intell. (2018)
Keyphrases
  • reinforcement learning
  • significant improvement
  • state space
  • action selection
  • computational cost
  • empirical studies
  • benchmark datasets
  • monte carlo
  • temporal difference
  • control problems
  • function approximators