Matches in SemOpenAlex for { <https://semopenalex.org/work/W2070619758> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W2070619758 endingPage "1155" @default.
- W2070619758 startingPage "1143" @default.
- W2070619758 abstract "One of the difficulties encountered in the application of the reinforcement learning to real-world problems is the construction of a discrete state space from a continuous sensory input signal. In the absence of a priori knowledge about the task, a straightforward approach to this problem is to discretize the input space into a grid, and to use a lookup table. However, this method suffers from the curse of dimensionality. Some studies use continuous function approximators such as neural networks instead of lookup tables. However, when global basis functions such as sigmoid functions are used, convergence cannot be guaranteed. To overcome this problem, we propose a method in which local basis functions are incrementally assigned depending on the task requirement. Initially, only one basis function is allocated over the entire space. The basis function is divided according to the statistical property of locally weighted temporal difference error (TD error) of the value function. We applied this method to an autonomous robot collision avoidance problem, and evaluated the validity of the algorithm in simulation. The proposed algorithm, which we call adaptive basis division (ABD) algorithm, achieved the task using a smaller number of basis functions than the conventional methods. Moreover, we applied the method to a goal-directed navigation problem of a real mobile robot. The action strategy was learned using a database of sensor data, and it was then used for navigation of a real machine. The robot reached the goal using a smaller number of internal states than with the conventional methods." @default.
- W2070619758 created "2016-06-24" @default.
- W2070619758 creator A5049494554 @default.
- W2070619758 creator A5085590930 @default.
- W2070619758 date "1999-10-01" @default.
- W2070619758 modified "2023-10-18" @default.
- W2070619758 title "Adaptive internal state space construction method for reinforcement learning of a real-world agent" @default.
- W2070619758 cites W1507281396 @default.
- W2070619758 cites W1689445748 @default.
- W2070619758 cites W1898758362 @default.
- W2070619758 cites W2091565802 @default.
- W2070619758 cites W2114865067 @default.
- W2070619758 cites W2171277043 @default.
- W2070619758 cites W3041202696 @default.
- W2070619758 cites W4231226883 @default.
- W2070619758 doi "https://doi.org/10.1016/s0893-6080(99)00055-6" @default.
- W2070619758 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/12662650" @default.
- W2070619758 hasPublicationYear "1999" @default.
- W2070619758 type Work @default.
- W2070619758 sameAs 2070619758 @default.
- W2070619758 citedByCount "55" @default.
- W2070619758 countsByYear W20706197582012 @default.
- W2070619758 countsByYear W20706197582013 @default.
- W2070619758 countsByYear W20706197582014 @default.
- W2070619758 countsByYear W20706197582017 @default.
- W2070619758 countsByYear W20706197582019 @default.
- W2070619758 countsByYear W20706197582020 @default.
- W2070619758 crossrefType "journal-article" @default.
- W2070619758 hasAuthorship W2070619758A5049494554 @default.
- W2070619758 hasAuthorship W2070619758A5085590930 @default.
- W2070619758 hasConcept C105795698 @default.
- W2070619758 hasConcept C111030470 @default.
- W2070619758 hasConcept C12426560 @default.
- W2070619758 hasConcept C134306372 @default.
- W2070619758 hasConcept C154945302 @default.
- W2070619758 hasConcept C162324750 @default.
- W2070619758 hasConcept C2524010 @default.
- W2070619758 hasConcept C2777303404 @default.
- W2070619758 hasConcept C33923547 @default.
- W2070619758 hasConcept C41008148 @default.
- W2070619758 hasConcept C50522688 @default.
- W2070619758 hasConcept C50644808 @default.
- W2070619758 hasConcept C5917680 @default.
- W2070619758 hasConcept C72434380 @default.
- W2070619758 hasConcept C91873725 @default.
- W2070619758 hasConcept C97541855 @default.
- W2070619758 hasConceptScore W2070619758C105795698 @default.
- W2070619758 hasConceptScore W2070619758C111030470 @default.
- W2070619758 hasConceptScore W2070619758C12426560 @default.
- W2070619758 hasConceptScore W2070619758C134306372 @default.
- W2070619758 hasConceptScore W2070619758C154945302 @default.
- W2070619758 hasConceptScore W2070619758C162324750 @default.
- W2070619758 hasConceptScore W2070619758C2524010 @default.
- W2070619758 hasConceptScore W2070619758C2777303404 @default.
- W2070619758 hasConceptScore W2070619758C33923547 @default.
- W2070619758 hasConceptScore W2070619758C41008148 @default.
- W2070619758 hasConceptScore W2070619758C50522688 @default.
- W2070619758 hasConceptScore W2070619758C50644808 @default.
- W2070619758 hasConceptScore W2070619758C5917680 @default.
- W2070619758 hasConceptScore W2070619758C72434380 @default.
- W2070619758 hasConceptScore W2070619758C91873725 @default.
- W2070619758 hasConceptScore W2070619758C97541855 @default.
- W2070619758 hasIssue "7-8" @default.
- W2070619758 hasLocation W20706197581 @default.
- W2070619758 hasLocation W20706197582 @default.
- W2070619758 hasOpenAccess W2070619758 @default.
- W2070619758 hasPrimaryLocation W20706197581 @default.
- W2070619758 hasRelatedWork W1976114455 @default.
- W2070619758 hasRelatedWork W2031695474 @default.
- W2070619758 hasRelatedWork W2121296643 @default.
- W2070619758 hasRelatedWork W2171493306 @default.
- W2070619758 hasRelatedWork W2312998612 @default.
- W2070619758 hasRelatedWork W2347245575 @default.
- W2070619758 hasRelatedWork W2372300130 @default.
- W2070619758 hasRelatedWork W27322302 @default.
- W2070619758 hasRelatedWork W2740042657 @default.
- W2070619758 hasRelatedWork W2963359646 @default.
- W2070619758 hasVolume "12" @default.
- W2070619758 isParatext "false" @default.
- W2070619758 isRetracted "false" @default.
- W2070619758 magId "2070619758" @default.
- W2070619758 workType "article" @default.