Search results for " Reinforcement"

showing 10 items of 51 documents

Can Interpretable Reinforcement Learning Manage Prosperity Your Way?

2022

Personalisation of products and services is fast becoming the driver of success in banking and commerce. Machine learning holds the promise of gaining a deeper understanding of and tailoring to customers’ needs and preferences. Whereas traditional solutions to financial decision problems frequently rely on model assumptions, reinforcement learning is able to exploit large amounts of data to improve customer modelling and decision-making in complex financial environments with fewer assumptions. Model explainability and interpretability present challenges from a regulatory perspective which demands transparency for acceptance; they also offer the opportunity for improved insight into and unde…

FOS: Computer and information sciencesComputer Science - Machine LearningArtificial Intelligence (cs.AI)Computer Science - Artificial IntelligenceGeneral Earth and Planetary SciencesAI in banking; personalized services; prosperity management; explainable AI; reinforcement learning; policy regularisationVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550General Environmental ScienceMachine Learning (cs.LG)AI; Volume 3; Issue 2; Pages: 526-537
researchProduct

Expanding the Active Inference Landscape: More Intrinsic Motivations in the Perception-Action Loop

2018

Active inference is an ambitious theory that treats perception, inference and action selection of autonomous agents under the heading of a single principle. It suggests biologically plausible explanations for many cognitive phenomena, including consciousness. In active inference, action selection is driven by an objective function that evaluates possible future actions with respect to current, inferred beliefs about the world. Active inference at its core is independent from extrinsic rewards, resulting in a high level of robustness across e.g.\ different environments or agent morphologies. In the literature, paradigms that share this independence have been summarised under the notion of in…

FOS: Computer and information sciencesComputer scienceComputer Science - Artificial Intelligencepredictive informationBiomedical EngineeringInferenceSystems and Control (eess.SY)02 engineering and technologyAction selectionI.2.0; I.2.6; I.5.0; I.5.1lcsh:RC321-57103 medical and health sciences0302 clinical medicineactive inferenceArtificial IntelligenceFOS: Electrical engineering electronic engineering information engineering0202 electrical engineering electronic engineering information engineeringFormal concept analysisMethodsperception-action loopuniversal reinforcement learningintrinsic motivationlcsh:Neurosciences. Biological psychiatry. NeuropsychiatryFree energy principleCognitive scienceRobotics and AII.5.0I.5.1I.2.6Partially observable Markov decision processI.2.0Artificial Intelligence (cs.AI)Action (philosophy)empowermentIndependence (mathematical logic)free energy principleComputer Science - Systems and Control020201 artificial intelligence & image processingBiological plausibility62F15 91B06030217 neurology & neurosurgeryvariational inference
researchProduct

On the use of Deep Reinforcement Learning for Visual Tracking: a Survey

2021

This paper aims at highlighting cutting-edge research results in the field of visual tracking by deep reinforcement learning. Deep reinforcement learning (DRL) is an emerging area combining recent progress in deep and reinforcement learning. It is showing interesting results in the computer vision field and, recently, it has been applied to the visual tracking problem yielding to the rapid development of novel tracking strategies. After providing an introduction to reinforcement learning, this paper compares recent visual tracking approaches based on deep reinforcement learning. Analysis of the state-of-the-art suggests that reinforcement learning allows modeling varying parts of the tracki…

General Computer ScienceComputer scienceFeature extractionMachine learningcomputer.software_genreField (computer science)video-surveillanceMinimum bounding boxReinforcement learningGeneral Materials ScienceSettore ING-INF/05 - Sistemi Di Elaborazione Delle Informazionideep reinforcement learningComputer vision machine learning video-surveillance deep reinforcement learning visual tracking.business.industryGeneral EngineeringTracking systemvisual trackingVisualizationActive appearance modelTK1-9971machine learningEye trackingComputer visionArtificial intelligenceElectrical engineering. Electronics. Nuclear engineeringbusinesscomputer
researchProduct

Development of a Simulator for Prototyping Reinforcement Learning-Based Autonomous Cars

2022

Autonomous driving is a research field that has received attention in recent years, with increasing applications of reinforcement learning (RL) algorithms. It is impractical to train an autonomous vehicle thoroughly in the physical space, i.e., the so-called ’real world’; therefore, simulators are used in almost all training of autonomous driving algorithms. There are numerous autonomous driving simulators, very few of which are specifically targeted at RL. RL-based cars are challenging due to the variety of reward functions available. There is a lack of simulators addressing many central RL research tasks within autonomous driving, such as scene understanding, localization and mapping, pla…

Human-Computer InteractionVDP::Teknologi: 500autonomous driving; simulators; reinforcement learningComputer Networks and CommunicationsCommunicationInformatics
researchProduct

The Mediating Role of Self-Efficacy in the Relationship between Approach Motivational System and Sports Success among Elite Speed Skating Athletes an…

2022

Background: While the association between self-efficacy and sports success has been well established in previous studies, little is known regarding whether the basic approach motivation system contributes to this relationship in athletes. The study examines associations between self-reported temperamental approach disposition, self-efficacy, and predispositions to sports success in athletes. Methods: A cross-sectional study was performed between August 3 and 30 November 2020. The participants were 156 athletes, aged 16–34 years (M = 21.57, SD = 3.58, 41.67% women), in two groups: 54 elite athletes in speed skating (EASS) and 102 physical education students (PES). The online survey consisted…

MaleMotivationPhysical Education and TrainingHealth Toxicology and MutagenesiseducationPublic Health Environmental and Occupational Healthapproach and avoidance temperament; elite athletes; physical education; Reinforcement Sensitivity Theory (RST); self-efficacy; speed skating; sports successSelf EfficacyCross-Sectional StudiesAthletesSkatingHumansFemaleStudentshuman activitiesInternational Journal of Environmental Research and Public Health; Volume 19; Issue 5; Pages: 2899
researchProduct

Acetaldehyde Oral Self-Administration: Evidence from the Operant-Conflict Paradigm

2011

Background: Acetaldehyde (ACD), ethanol's first metabolite, has been reported to interact with the dopaminergic reward system, and with the neural circuits involved in stress response. Rats self-administer ACD directly into cerebral ventricles, and multiple intracerebroventricular infusions of ACD produce conditioned place preference. Self-administration has been largely employed to assess the reinforcing and addictive properties of most drugs of abuse. In particular, operant conditioning is a valid model to investigate drug-seeking and drug-taking behavior in rats. Methods: This study was aimed at the evaluation of (i) the motivational properties of oral ACD in the induction and maintenanc…

MalePunishment (psychology)media_common.quotation_subjectAdministration OralMedicine (miscellaneous)Self AdministrationAcetaldehydePharmacologyToxicologyDevelopmental psychologyConflict PsychologicalReward systemAnimalsRats WistarReinforcementmedia_commonAcetaldehyde Lever-Pressing Punishment Reinforcement Relapse.AddictionDopaminergicAbstinenceConditioned place preferenceRatsPsychiatry and Mental healthSettore BIO/14 - FarmacologiaConditioning OperantSelf-administrationPsychology
researchProduct

Transgraft sac Embolization Combined with Graft Reinforcement for Refractory Mixed-Type Endoleak.

2018

International audience; An 80-year-old female underwent EVAR 4 years ago. She presented type II endoleak with sac expansion from 68 to 80 mm during 3-year follow-up after EVAR. Although she underwent translumbar percutaneous sac embolization, the AAA sac continued to enlarge, suggesting mixed-type endoleak including type I, II, and III. Transgraft direct sac angiography revealed endoleak cavity without demonstrable feeding vessel. Transgraft sac embolization using n-butyl cyanoacrylate and graft reinforcement was performed concurrently, without complications. The graft reinforcement consisted of graft extension for eliminating occult type I endoleak, and relining for eliminating occult type…

MaleReoperationmedicine.medical_specialtyTransgraft sac embolizationPercutaneousEndoleakmedicine.medical_treatmentMixed typeAortographyGraft reinforcement030218 nuclear medicine & medical imaginglaw.invention03 medical and health sciencesBlood Vessel Prosthesis Implantation0302 clinical medicine[SDV.MHEP.CSC]Life Sciences [q-bio]/Human health and pathology/Cardiology and cardiovascular systemRefractoryMixed-type endoleaklawn-butyl cyanoacrylatemedicineHumansEVARRadiology Nuclear Medicine and imagingEmbolizationAged[SDV.IB] Life Sciences [q-bio]/BioengineeringAged 80 and overmedicine.diagnostic_testbusiness.industryN-butyl-cyanoacrylateEndovascular ProceduresEnbucrilateCombined Modality TherapyEmbolization Therapeutic[SDV.MHEP.CSC] Life Sciences [q-bio]/Human health and pathology/Cardiology and cardiovascular systemSurgeryTreatment OutcomeCyanoacrylateAngiography[SDV.IB]Life Sciences [q-bio]/BioengineeringFemaleStentsCardiology and Cardiovascular MedicinebusinessTomography X-Ray ComputedAortic Aneurysm AbdominalCardiovascular and interventional radiology
researchProduct

Designing a multi-layer edge-computing platform for energy-efficient and delay-aware offloading in vehicular networks

2021

Abstract Vehicular networks are expected to support many time-critical services requiring huge amounts of computation resources with very low delay. However, such requirements may not be fully met by vehicle on-board devices due to their limited processing and storage capabilities. The solution provided by 5G is the application of the Multi-Access Edge Computing (MEC) paradigm, which represents a low-latency alternative to remote clouds. Accordingly, we envision a multi-layer job-offloading scheme based on three levels, i.e., the Vehicular Domain, the MEC Domain and Backhaul Network Domain. In such a view, jobs can be offloaded from the Vehicular Domain to the MEC Domain, and even further o…

Markov ModelsVehicular ad hoc networkComputer Networks and CommunicationsComputer scienceDistributed computing5G; Edge Computing; Markov Models; Reinforcement Learning; Vehicular NetworksLoad balancing (computing)Reinforcement LearningDomain (software engineering)ServerEdge ComputingReinforcement learningVehicular NetworksMarkov decision process5GEdge computingEfficient energy useComputer Networks
researchProduct

Brick Masonry Columns Externally Wrapped with Steel Wires under Concentric and Eccentric Loads

2017

This paper discusses an experimental investigation of clay brick columns that are externally strengthened by steel wire collars wrapping the horizontal mortar joints. The study aims to prove the effectiveness of the proposed strengthening technique and detect the efficiency of different numbers of steel collars. Additionally, the effect of eccentric loading is investigated. This paper proves that an analytical expression available in the previous literature can be modified to provide the strength of the equivalent homogeneous cross section in simple compression. To this aim, the biaxial strength domain of the bricks is modified to account for the lateral pressure exerted by the steel collar…

Materials science0211 other engineering and technologiesMasonry veneer020101 civil engineeringExternal reinforcement02 engineering and technologyConcentric0201 civil engineering021105 building & constructionGeneral Materials ScienceGeotechnical engineeringCivil and Structural Engineeringbusiness.industryBuilding and ConstructionStructural engineeringMasonryStrength of materialsSteel collarStrength domainMechanics of MaterialsBrick masonryBrick masonryClay brickMaterials Science (all)MortarbusinessJournal of Materials in Civil Engineering
researchProduct

Preparation and Characterization of Composites Materials with Rubber Matrix and with Polyvinyl Chloride Addition (PVC)

2020

An important problem that arises at present refers to the increase in performances in the exploitation of the conveyor belts. Additionally, it is pursued to use some materials, which can be obtained by recycling rubber and PVC waste, in their structure. Thus, the research aimed at creating conveyor belts using materials obtained from the recycling of rubber and PVC waste. Under these conditions, conveyor belts were made that had in their structure two types of rubber and PVC, which was obtained by adding in certain proportions of reclaimed rubber and powder obtained from grinding rubber waste. In order to study the effect of adding PVC on properties, four types of conveyor belts were made, …

Materials sciencePolymers and Plasticsfinite element methodrubber02 engineering and technologyTensile strain010402 general chemistry01 natural sciencesArticlelcsh:QD241-441chemistry.chemical_compoundlcsh:Organic chemistryNatural rubberaccelerated agingComposite materialTextile reinforcementGeneral Chemistry021001 nanoscience & nanotechnologymaterials structure analysisAccelerated aging0104 chemical sciencesGrindingPolyvinyl chloridechemistryvisual_artvisual_art.visual_art_mediumpolyvinyl chloride0210 nano-technologyPolymers
researchProduct