16 citations · 86 across the 20 of their papers we have counts for
4 papers · 2 filters
Eligibility Propagation to Speed up Time Hopping for Reinforcement Learning
Petar Kormushev, Kohei Nomoto, Fangyan Dong +1
A mechanism called Eligibility Propagation is proposed to speed up the Time Hopping technique used for faster Reinforcement Learning in simulations. Eligibility Propagation provide…
Design, development and implementation of a tool for construction of declarative functional descriptions of semantic web services based on WSMO methodology
Petar Kormushev
Semantic web services (SWS) are self-contained, self-describing, semantically marked-up software resources that can be published, discovered, composed and executed across the Web i…
Time Hopping technique for faster reinforcement learning in simulations
Petar Kormushev, Kohei Nomoto, Fangyan Dong +1
This preprint has been withdrawn by the author for revision
Time manipulation technique for speeding up reinforcement learning in simulations
Petar Kormushev, Kohei Nomoto, Fangyan Dong +1
A technique for speeding up reinforcement learning algorithms by using time manipulation is proposed. It is applicable to failure-avoidance control problems running in a computer s…