Safe reinforcement learning in high-risk tasks through policy improvement

  1. Garcia Polo, F.J.
  2. Fernandez Rebollo, F.
Konferenzberichte:
IEEE SSCI 2011: Symposium Series on Computational Intelligence - ADPRL 2011: 2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning

ISBN: 9781424498888

Datum der Publikation: 2011

Seiten: 76-83

Art: Konferenz-Beitrag

DOI: 10.1109/ADPRL.2011.5967356 GOOGLE SCHOLAR