Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT

Freigegeben

Zeitschriftenartikel

Parameter-exploring policy gradients

MPG-Autoren
/persons/resource/persons84135

Peters,  J.
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

Volltexte (beschränkter Zugriff)
Für Ihren IP-Bereich sind aktuell keine Volltexte freigegeben.
Volltexte (frei zugänglich)
Es sind keine frei zugänglichen Volltexte in PuRe verfügbar
Ergänzendes Material (frei zugänglich)
Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar
Zitation

Sehnke, F., Osendorfer, C., Rückstiess, T., Graves, A., Peters, J., & Schmidhuber, J. (2010). Parameter-exploring policy gradients. Neural networks, 21(4), 551-559. doi:10.1016/j.neunet.2009.12.004.


Zitierlink: https://hdl.handle.net/11858/00-001M-0000-0013-C026-2
Zusammenfassung
We present a model-free reinforcement learning method for partially observable Markov decision problems. Our method estimates a likelihood gradient by sampling directly in parameter space, which leads to lower variance gradient estimates than obtained by regular policy gradient methods. We show that for several complex control tasks, including robust standing with a humanoid robot, this method outperforms well-known algorithms from the fields of standard policy gradients, finite difference methods and population based heuristics. We also show that the improvement is largest when the parameter samples are drawn symmetrically. Lastly we analyse the importance of the individual components of our method by incrementally incorporating them into the other algorithms, and measuring the gain in performance after each step.