Matches in SemOpenAlex for { <https://semopenalex.org/work/W48211654> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W48211654 abstract "Robot learning such as reinforcement learning generally needs a well-de ned state space in order to converge. However, to build such a state space is one of the main issues of the robot learning because of the inter-dependence between state and action spaces, which resembles to the well known chicken and egg problem. This paper proposes two methods of actionbased state space construction for vision-based mobile robots. Basic ideas common to the two methods to cope with the inter-dependence are that we de ne a state as a cluster of of input vectors from which the robot can reach the goal state or the state already obtained by a sequence of one kind action primitive regardless of its length, and that this sequence is de ned as one action. The rst method clusters the input vectors as hyper ellipsoids so that the whole state space is segmented into a state transition map in terms of action from which the optimal action sequence is obtained. In order to obtain the such a map, we need a su cient number of data, which means longer learning time. To cope with this, we proposed the second method by which a robot learns purposive behavior within less learning time by incrementally segmenting the sensor space based on the experiences of the robot. The incremental segmentation is performed by constructing local models in the state space, which is based on the function approximation of the sensor outputs to reduce the learning time and on the reinforcement signal to emerge a purposive behavior. To show the validity of the methods, we apply them to a soccer robot which tries to shoot a ball into a goal. The simulation and real experiments are shown." @default.
- W48211654 created "2016-06-24" @default.
- W48211654 creator A5044985800 @default.
- W48211654 creator A5047992433 @default.
- W48211654 creator A5089803467 @default.
- W48211654 date "2007-01-01" @default.
- W48211654 modified "2023-09-23" @default.
- W48211654 title "Sensor Space Segmentation for Mobile Robot Learning" @default.
- W48211654 cites W145683767 @default.
- W48211654 cites W1508050220 @default.
- W48211654 cites W1522153944 @default.
- W48211654 cites W1557517019 @default.
- W48211654 cites W1640646391 @default.
- W48211654 cites W1827383950 @default.
- W48211654 cites W1853060676 @default.
- W48211654 cites W2096938516 @default.
- W48211654 cites W2109952767 @default.
- W48211654 cites W2198041288 @default.
- W48211654 cites W2913060459 @default.
- W48211654 cites W3011120880 @default.
- W48211654 hasPublicationYear "2007" @default.
- W48211654 type Work @default.
- W48211654 sameAs 48211654 @default.
- W48211654 citedByCount "2" @default.
- W48211654 countsByYear W482116542012 @default.
- W48211654 crossrefType "journal-article" @default.
- W48211654 hasAuthorship W48211654A5044985800 @default.
- W48211654 hasAuthorship W48211654A5047992433 @default.
- W48211654 hasAuthorship W48211654A5089803467 @default.
- W48211654 hasConcept C105795698 @default.
- W48211654 hasConcept C11413529 @default.
- W48211654 hasConcept C121332964 @default.
- W48211654 hasConcept C154945302 @default.
- W48211654 hasConcept C188888258 @default.
- W48211654 hasConcept C19966478 @default.
- W48211654 hasConcept C2778112365 @default.
- W48211654 hasConcept C2780791683 @default.
- W48211654 hasConcept C31972630 @default.
- W48211654 hasConcept C33923547 @default.
- W48211654 hasConcept C41008148 @default.
- W48211654 hasConcept C48103436 @default.
- W48211654 hasConcept C54355233 @default.
- W48211654 hasConcept C62520636 @default.
- W48211654 hasConcept C72434380 @default.
- W48211654 hasConcept C86803240 @default.
- W48211654 hasConcept C90509273 @default.
- W48211654 hasConcept C97541855 @default.
- W48211654 hasConceptScore W48211654C105795698 @default.
- W48211654 hasConceptScore W48211654C11413529 @default.
- W48211654 hasConceptScore W48211654C121332964 @default.
- W48211654 hasConceptScore W48211654C154945302 @default.
- W48211654 hasConceptScore W48211654C188888258 @default.
- W48211654 hasConceptScore W48211654C19966478 @default.
- W48211654 hasConceptScore W48211654C2778112365 @default.
- W48211654 hasConceptScore W48211654C2780791683 @default.
- W48211654 hasConceptScore W48211654C31972630 @default.
- W48211654 hasConceptScore W48211654C33923547 @default.
- W48211654 hasConceptScore W48211654C41008148 @default.
- W48211654 hasConceptScore W48211654C48103436 @default.
- W48211654 hasConceptScore W48211654C54355233 @default.
- W48211654 hasConceptScore W48211654C62520636 @default.
- W48211654 hasConceptScore W48211654C72434380 @default.
- W48211654 hasConceptScore W48211654C86803240 @default.
- W48211654 hasConceptScore W48211654C90509273 @default.
- W48211654 hasConceptScore W48211654C97541855 @default.
- W48211654 hasOpenAccess W48211654 @default.
- W48211654 hasRelatedWork W1481095334 @default.
- W48211654 hasRelatedWork W1503862567 @default.
- W48211654 hasRelatedWork W155730701 @default.
- W48211654 hasRelatedWork W1898758362 @default.
- W48211654 hasRelatedWork W1958088497 @default.
- W48211654 hasRelatedWork W1974960581 @default.
- W48211654 hasRelatedWork W2126521188 @default.
- W48211654 hasRelatedWork W2138489334 @default.
- W48211654 hasRelatedWork W2152166054 @default.
- W48211654 hasRelatedWork W2155754001 @default.
- W48211654 hasRelatedWork W2330038526 @default.
- W48211654 hasRelatedWork W2533945995 @default.
- W48211654 hasRelatedWork W2544716473 @default.
- W48211654 hasRelatedWork W2545038291 @default.
- W48211654 hasRelatedWork W2893178414 @default.
- W48211654 hasRelatedWork W2945212863 @default.
- W48211654 hasRelatedWork W2952101550 @default.
- W48211654 hasRelatedWork W2999580272 @default.
- W48211654 hasRelatedWork W3023923733 @default.
- W48211654 hasRelatedWork W3090346377 @default.
- W48211654 isParatext "false" @default.
- W48211654 isRetracted "false" @default.
- W48211654 magId "48211654" @default.
- W48211654 workType "article" @default.