Time Hopping technique for faster reinforcement learning in simulations

Petar Kormushev; Kohei Nomoto; Fangyan Dong; Kaoru Hirota

Time Hopping technique for faster reinforcement learning in simulations

Artificial Intelligence 2011-09-07 v2 Machine Learning Robotics

Authors: Petar Kormushev , Kohei Nomoto , Fangyan Dong , Kaoru Hirota

View on arXiv ↗ PDF ↗

Abstract

This preprint has been withdrawn by the author for revision

Cite

@article{arxiv.0904.0545,
  title  = {Time Hopping technique for faster reinforcement learning in simulations},
  author = {Petar Kormushev and Kohei Nomoto and Fangyan Dong and Kaoru Hirota},
  journal= {arXiv preprint arXiv:0904.0545},
  year   = {2011}
}