Sign in

Exploiting the Sign of the Advantage Function to Learn Deterministic Policies in Continuous Domains.

Matthieu ZimmerPaul Weng
Published in: IJCAI (2019)
Keyphrases
  • continuous domains
  • genetic algorithm
  • evolutionary computation
  • evolutionary algorithm
  • higher dimensional
  • artificial neural networks
  • particle swarm optimization
  • conditional independence