Matches in SemOpenAlex for { <https://semopenalex.org/work/W2066461256> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2066461256 abstract "An autonomous robot, which makes decisions based on previous experience and feedback from its sensors is one of the challenges in robotics. Among the most promising framework to bring traditional robotics towards true autonomy is reinforcement learning. However, reinforcement learning in high dimensional spaces usually required to encode robot tasks is extremely difficult. The key idea to speed up the reinforcement learning is to limit the potentially huge search space of the policy by using previous experience and to generalize to new policies from similar cases. In the paper we evaluate this idea on learning of ball-in-a-cup playing robot. First we solve this problem using traditional approach by learning action-value function without using any previous knowledge. Next, we propose learning which relies on generalizing to new policies from similar cases. It is shown, that this latter approach dramatically reduces number cycles needed to learn the appropriate policy." @default.
- W2066461256 created "2016-06-24" @default.
- W2066461256 creator A5019399129 @default.
- W2066461256 creator A5020114289 @default.
- W2066461256 date "2011-12-01" @default.
- W2066461256 modified "2023-09-25" @default.
- W2066461256 title "Reinforcement learning of ball-in-a-cup playing robot" @default.
- W2066461256 cites W1516801383 @default.
- W2066461256 cites W1746819321 @default.
- W2066461256 cites W1910378657 @default.
- W2066461256 cites W1967097499 @default.
- W2066461256 cites W1975318316 @default.
- W2066461256 cites W2012392077 @default.
- W2066461256 cites W2041812416 @default.
- W2066461256 cites W2110304639 @default.
- W2066461256 cites W2116226448 @default.
- W2066461256 cites W2119717200 @default.
- W2066461256 cites W2121863487 @default.
- W2066461256 cites W2124758444 @default.
- W2066461256 cites W2125612430 @default.
- W2066461256 cites W2148467756 @default.
- W2066461256 cites W2161872510 @default.
- W2066461256 cites W2166302491 @default.
- W2066461256 cites W2312442049 @default.
- W2066461256 doi "https://doi.org/10.1109/robio.2011.6181710" @default.
- W2066461256 hasPublicationYear "2011" @default.
- W2066461256 type Work @default.
- W2066461256 sameAs 2066461256 @default.
- W2066461256 citedByCount "5" @default.
- W2066461256 countsByYear W20664612562017 @default.
- W2066461256 countsByYear W20664612562018 @default.
- W2066461256 countsByYear W20664612562020 @default.
- W2066461256 countsByYear W20664612562021 @default.
- W2066461256 crossrefType "proceedings-article" @default.
- W2066461256 hasAuthorship W2066461256A5019399129 @default.
- W2066461256 hasAuthorship W2066461256A5020114289 @default.
- W2066461256 hasConcept C104317684 @default.
- W2066461256 hasConcept C119857082 @default.
- W2066461256 hasConcept C122041747 @default.
- W2066461256 hasConcept C134306372 @default.
- W2066461256 hasConcept C154945302 @default.
- W2066461256 hasConcept C185592680 @default.
- W2066461256 hasConcept C188888258 @default.
- W2066461256 hasConcept C199190896 @default.
- W2066461256 hasConcept C19966478 @default.
- W2066461256 hasConcept C33923547 @default.
- W2066461256 hasConcept C34413123 @default.
- W2066461256 hasConcept C41008148 @default.
- W2066461256 hasConcept C55493867 @default.
- W2066461256 hasConcept C66746571 @default.
- W2066461256 hasConcept C90509273 @default.
- W2066461256 hasConcept C97541855 @default.
- W2066461256 hasConceptScore W2066461256C104317684 @default.
- W2066461256 hasConceptScore W2066461256C119857082 @default.
- W2066461256 hasConceptScore W2066461256C122041747 @default.
- W2066461256 hasConceptScore W2066461256C134306372 @default.
- W2066461256 hasConceptScore W2066461256C154945302 @default.
- W2066461256 hasConceptScore W2066461256C185592680 @default.
- W2066461256 hasConceptScore W2066461256C188888258 @default.
- W2066461256 hasConceptScore W2066461256C199190896 @default.
- W2066461256 hasConceptScore W2066461256C19966478 @default.
- W2066461256 hasConceptScore W2066461256C33923547 @default.
- W2066461256 hasConceptScore W2066461256C34413123 @default.
- W2066461256 hasConceptScore W2066461256C41008148 @default.
- W2066461256 hasConceptScore W2066461256C55493867 @default.
- W2066461256 hasConceptScore W2066461256C66746571 @default.
- W2066461256 hasConceptScore W2066461256C90509273 @default.
- W2066461256 hasConceptScore W2066461256C97541855 @default.
- W2066461256 hasLocation W20664612561 @default.
- W2066461256 hasOpenAccess W2066461256 @default.
- W2066461256 hasPrimaryLocation W20664612561 @default.
- W2066461256 hasRelatedWork W2065963568 @default.
- W2066461256 hasRelatedWork W2066461256 @default.
- W2066461256 hasRelatedWork W3022038857 @default.
- W2066461256 hasRelatedWork W3196155444 @default.
- W2066461256 hasRelatedWork W3210156800 @default.
- W2066461256 hasRelatedWork W4205156393 @default.
- W2066461256 hasRelatedWork W4297094728 @default.
- W2066461256 hasRelatedWork W4312812851 @default.
- W2066461256 hasRelatedWork W4319083788 @default.
- W2066461256 hasRelatedWork W78603744 @default.
- W2066461256 isParatext "false" @default.
- W2066461256 isRetracted "false" @default.
- W2066461256 magId "2066461256" @default.
- W2066461256 workType "article" @default.