Time Hopping technique for faster reinforcement learning in simulations

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

Sep-6-2011–arXiv.org Artificial Intelligence

This preprint has been withdrawn by the author for revision

artificial intelligence, machine learning, time hopping technique, (3 more...)

arXiv.org Artificial Intelligence

Sep-6-2011

arXiv.org Web Page

Genre:
- Research Report (0.40)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (0.40)