Qualitative Adaptive Reward Learning With Success Failure Maps: Applied to Humanoid Robot Walking

Document type :
Journal articles
Complete list of metadatas

https://hal-univ-tln.archives-ouvertes.fr/hal-01723809
Contributor : Claire Dune <>
Submitted on : Monday, March 5, 2018 - 5:50:48 PM
Last modification on : Wednesday, March 28, 2018 - 1:22:01 PM

Identifiers

  • HAL Id : hal-01723809, version 1

Collections

Citation

John Nassour, Vincent Hugel, Fethi Ben Ouezdou, Gordon Cheng. Qualitative Adaptive Reward Learning With Success Failure Maps: Applied to Humanoid Robot Walking. IEEE Transactions on Neural Networks and Learning Systems, IEEE, 2013, 24 (1), pp.81--93. ⟨hal-01723809⟩

Share

Metrics

Record views

68