000001465 001__ 1465
000001465 005__ 20141118153506.0
000001465 04107 $$acze
000001465 046__ $$k2003-05-12
000001465 100__ $$aBřezina, T.
000001465 24500 $$aWalking gait of four-legged robot obtained through Q-learning

000001465 24630 $$n9.$$pEngineering Mechanics 2003
000001465 260__ $$bInstitute of Theoretical and Applied Mechanics AS CR, Prague
000001465 506__ $$arestricted
000001465 520__ $$2eng$$aThe possible method of walking policy obtaining of four-legged robot through Q-learning is discussed in the contribution. Q-learning is implemented using architecture represented by non-deterministic state machine that defines both possible discrete states and admissible transitions between them. Discrete state is designed as indicators vector of goals achievement by single simultaneously activated instances of two basic controllers. Only simultaneous activations that guarantee static stability of robot are admissible even in the case when single activations cold not achieve its goals. The controllers attempt to achieve its goals using on-line minimization process. Q-learning sequentially improves an estimation of future benefit from usage of admissible simultaneous activations in single discrete states. Walking policy is generated through activations with the highest estimation of future benefit.

000001465 540__ $$aText je chráněný podle autorského zákona č. 121/2000 Sb.
000001465 653__ $$a

000001465 7112_ $$aEngineering Mechanics 2003$$cSvratka (CZ)$$d2003-05-12 / 2003-05-15$$gEM2003
000001465 720__ $$aBřezina, T.$$iSedlák, P.$$iSingule, V.$$iHouška, P.
000001465 8560_ $$ffischerc@itam.cas.cz
000001465 8564_ $$s1301227$$uhttps://invenio.itam.cas.cz/record/1465/files/193-Tomas-Brezina-PT.pdf$$y
             Original version of the author's contribution as presented on CD, MCT.
            
000001465 962__ $$r971
000001465 980__ $$aPAPER