FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2016475778> ?p ?o ?g. }

• W2016475778 endingPage "115" @default.
• W2016475778 startingPage "104" @default.
• W2016475778 abstract "The stabilization control of nonholonomic systems have been extensively studied because it is essential for nonholonomic robot control problems. The difficulty in this problem is that the theoretical derivation of control policy is not necessarily guaranteed achievable. In this paper, we present a reinforcement learning (RL) method with instance-based policy (IBP) representation, in which control policies for this class are optimized with respect to user-defined cost functions. Direct policy search (DPS) is an approach for RL; the policy is represented by parametric models and the model parameters are directly searched by optimization techniques including genetic algorithms (GAs). In IBP representation an instance consists of a state and an action pair; a policy consists of a set of instances. Several DPSs with IBP have been previously proposed. In these methods, sometimes fail to obtain optimal control policies when state-action variables are continuous. In this paper, we present a real-coded GA for DPSs with IBP. Our method is specifically designed for continuous domains. Optimization of IBP has three difficulties; high-dimensionality, epistasis, and multi-modality. Our solution is designed for overcoming these difficulties. The policy search with IBP representation appears to be high-dimensional optimization; however, instances which can improve the fitness are often limited to active instances (instances used for the evaluation). In fact, the number of active instances is small. Therefore, we treat the search problem as a low dimensional problem by restricting search variables only to active instances. It has been commonly known that functions with epistasis can be efficiently optimized with crossovers which satisfy the inheritance of statistics. For efficient search of IBP, we propose extended crossover-like mutation (extended XLM) which generates a new instance around an instance with satisfying the inheritance of statistics. For overcoming multi-modality, we propose extended CCM for selection. Extended CCM always chooses the child for next generation among children and a parent which generates the children. By doing so, the diversity of the population is expected to be well maintained. Our proposals, FLIP (Functionally sophisticated Learner for IBP), consist of extended XLM and extended CCM. The effectiveness of FLIP is shown by experiments with nonholonomic control problems, a space robot, a car-like robot, and a parallel-type double inverted pendulum." @default.
• W2016475778 created "2016-06-24" @default.
• W2016475778 creator A5003520894 @default.
• W2016475778 creator A5022139141 @default.
• W2016475778 creator A5083317982 @default.
• W2016475778 creator A5085725359 @default.
• W2016475778 date "2009-01-01" @default.
• W2016475778 modified "2023-10-01" @default.
• W2016475778 title "Instance-based Policy Learning by Real-coded Genetic Algorithms and Its Application to Control of Nonholonomic Systems" @default.
• W2016475778 cites W1578647949 @default.
• W2016475778 cites W1687991450 @default.
• W2016475778 cites W1914583973 @default.
• W2016475778 cites W2049287437 @default.
• W2016475778 cites W2121863487 @default.
• W2016475778 cites W2133361850 @default.
• W2016475778 cites W2154549708 @default.
• W2016475778 cites W2165299353 @default.
• W2016475778 cites W2273483390 @default.
• W2016475778 cites W2291458045 @default.
• W2016475778 cites W2320066179 @default.
• W2016475778 cites W2326725832 @default.
• W2016475778 cites W2331265447 @default.
• W2016475778 cites W2334750645 @default.
• W2016475778 cites W2585391487 @default.
• W2016475778 doi "https://doi.org/10.1527/tjsai.24.104" @default.
• W2016475778 hasPublicationYear "2009" @default.
• W2016475778 type Work @default.
• W2016475778 sameAs 2016475778 @default.
• W2016475778 citedByCount "11" @default.
• W2016475778 countsByYear W20164757782012 @default.
• W2016475778 countsByYear W20164757782016 @default.
• W2016475778 countsByYear W20164757782017 @default.
• W2016475778 crossrefType "journal-article" @default.
• W2016475778 hasAuthorship W2016475778A5003520894 @default.
• W2016475778 hasAuthorship W2016475778A5022139141 @default.
• W2016475778 hasAuthorship W2016475778A5083317982 @default.
• W2016475778 hasAuthorship W2016475778A5085725359 @default.
• W2016475778 hasBestOaLocation W20164757781 @default.
• W2016475778 hasConcept C111030470 @default.
• W2016475778 hasConcept C126255220 @default.
• W2016475778 hasConcept C154945302 @default.
• W2016475778 hasConcept C177264268 @default.
• W2016475778 hasConcept C17744445 @default.
• W2016475778 hasConcept C199360897 @default.
• W2016475778 hasConcept C199539241 @default.
• W2016475778 hasConcept C2776359362 @default.
• W2016475778 hasConcept C33923547 @default.
• W2016475778 hasConcept C41008148 @default.
• W2016475778 hasConcept C94625758 @default.
• W2016475778 hasConcept C97541855 @default.
• W2016475778 hasConceptScore W2016475778C111030470 @default.
• W2016475778 hasConceptScore W2016475778C126255220 @default.
• W2016475778 hasConceptScore W2016475778C154945302 @default.
• W2016475778 hasConceptScore W2016475778C177264268 @default.
• W2016475778 hasConceptScore W2016475778C17744445 @default.
• W2016475778 hasConceptScore W2016475778C199360897 @default.
• W2016475778 hasConceptScore W2016475778C199539241 @default.
• W2016475778 hasConceptScore W2016475778C2776359362 @default.
• W2016475778 hasConceptScore W2016475778C33923547 @default.
• W2016475778 hasConceptScore W2016475778C41008148 @default.
• W2016475778 hasConceptScore W2016475778C94625758 @default.
• W2016475778 hasConceptScore W2016475778C97541855 @default.
• W2016475778 hasIssue "1" @default.
• W2016475778 hasLocation W20164757781 @default.
• W2016475778 hasOpenAccess W2016475778 @default.
• W2016475778 hasPrimaryLocation W20164757781 @default.
• W2016475778 hasRelatedWork W1578647949 @default.
• W2016475778 hasRelatedWork W2188649388 @default.
• W2016475778 hasRelatedWork W2553033844 @default.
• W2016475778 hasRelatedWork W2556555801 @default.
• W2016475778 hasRelatedWork W2607264901 @default.
• W2016475778 hasRelatedWork W2948009385 @default.
• W2016475778 hasRelatedWork W2953441850 @default.
• W2016475778 hasRelatedWork W2972514911 @default.
• W2016475778 hasRelatedWork W2977703466 @default.
• W2016475778 hasRelatedWork W2994967491 @default.
• W2016475778 hasRelatedWork W3010966539 @default.
• W2016475778 hasRelatedWork W3036705889 @default.
• W2016475778 hasRelatedWork W3096080671 @default.
• W2016475778 hasRelatedWork W3098068565 @default.
• W2016475778 hasRelatedWork W3115662629 @default.
• W2016475778 hasRelatedWork W3119344485 @default.
• W2016475778 hasRelatedWork W3127407558 @default.
• W2016475778 hasRelatedWork W3186949135 @default.
• W2016475778 hasRelatedWork W745087674 @default.
• W2016475778 hasRelatedWork W80218507 @default.
• W2016475778 hasVolume "24" @default.
• W2016475778 isParatext "false" @default.
• W2016475778 isRetracted "false" @default.
• W2016475778 magId "2016475778" @default.
• W2016475778 workType "article" @default.