Reinforcement learning in dynamic environment: abstraction of state-action space utilizing properties of the robot body and environment
Crossref DOI link: https://doi.org/10.1007/s10015-015-0258-1
Published Online: 2016-01-18
Published Print: 2016-03
Update policy: https://doi.org/10.1007/springer_crossmark_policy
Ito, Kazuyuki
Takeuchi, Yutaka
Text and Data Mining valid from 2016-01-18