Search results for "force"

showing 10 items of 3423 documents

Assigning discounts in a marketing campaign by using reinforcement learning and neural networks

2009

In this work, RL is used to find an optimal policy for a marketing campaign. Data show a complex characterization of state and action spaces. Two approaches are proposed to circumvent this problem. The first approach is based on the self-organizing map (SOM), which is used to aggregate states. The second approach uses a multilayer perceptron (MLP) to carry out a regression of the action-value function. The results indicate that both approaches can improve a targeted marketing campaign. Moreover, the SOM approach allows an intuitive interpretation of the results, and the MLP approach yields robust results with generalization capabilities.

Artificial neural networkComputer scienceGeneralizationbusiness.industrymedia_common.quotation_subjectAggregate (data warehouse)General EngineeringMachine learningcomputer.software_genreComputer Science ApplicationsFunction approximationArtificial IntelligenceMultilayer perceptronReinforcement learningState (computer science)Artificial intelligenceFunction (engineering)businesscomputermedia_commonExpert Systems with Applications
researchProduct

Safer Reinforcement Learning for Agents in Industrial Grid-Warehousing

2020

In mission-critical, real-world environments, there is typically a low threshold for failure, which makes interaction with learning algorithms particularly challenging. Here, current state-of-the-art reinforcement learning algorithms struggle to learn optimal control policies safely. Loss of control follows, which could result in equipment breakages and even personal injuries.

Artificial neural networkComputer scienceSAFERControl (management)0202 electrical engineering electronic engineering information engineeringReinforcement learning020206 networking & telecommunications02 engineering and technologyMarkov decision processGridOptimal controlIndustrial engineering
researchProduct

Increasing sample efficiency in deep reinforcement learning using generative environment modelling

2020

Artificial neural networkComputer sciencebusiness.industrySample (statistics)Machine learningcomputer.software_genreTheoretical Computer ScienceComputational Theory and MathematicsArtificial IntelligenceControl and Systems EngineeringReinforcement learningMarkov decision processArtificial intelligencebusinesscomputerVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550Generative grammar
researchProduct

Road Detection for Reinforcement Learning Based Autonomous Car

2020

Human mistakes in traffic often have terrible consequences. The long-awaited introduction of self-driving vehicles may solve many of the problems with traffic, but much research is still needed before cars are fully autonomous.In this paper, we propose a new Road Detection algorithm using online supervised learning based on a Neural Network architecture. This algorithm is designed to support a Reinforcement Learning algorithm (for example, the standard Proximal Policy Optimization or PPO) by detecting when the car is in an adverse condition. Specifically, the PPO gets a penalty whenever the virtual automobile gets stuck or drives off the road with any of its four wheels.Initial experiments …

Artificial neural networkComputer sciencebusiness.industrySupervised learningNeural network architectureReinforcement learningArtificial intelligenceReinforcement learning algorithmbusinessProceedings of the 2020 The 3rd International Conference on Information Science and System
researchProduct

CostNet: An End-to-End Framework for Goal-Directed Reinforcement Learning

2020

Reinforcement Learning (RL) is a general framework concerned with an agent that seeks to maximize rewards in an environment. The learning typically happens through trial and error using explorative methods, such as \(\epsilon \)-greedy. There are two approaches, model-based and model-free reinforcement learning, that show concrete results in several disciplines. Model-based RL learns a model of the environment for learning the policy while model-free approaches are fully explorative and exploitative without considering the underlying environment dynamics. Model-free RL works conceptually well in simulated environments, and empirical evidence suggests that trial and error lead to a near-opti…

Artificial neural networkEnd-to-end principlebusiness.industryComputer scienceReinforcement learningSample (statistics)Markov decision processArtificial intelligenceEmpirical evidenceTrial and errorbusinessFeature learning
researchProduct

Interannual and decadal SST-forced responses of the West African monsoon

2010

International audience; We review the studies carried out during the African Monsoon Multidisciplinary Analysis (AMMA)-EU on the changes of interannual sea surface temperature (SST)-West African monsoon (WAM) covariability at multidecadal timescales, together with the influence of global warming (GW). The results obtained in the AMMA-EU suggest the importance of the background state, modulated by natural and anthropogenic variability, in the appearance of different interannual modes. The lack of reliability of current coupled models in giving a realistic assessment for WAM in the future is also stated.

Atmospheric Science010504 meteorology & atmospheric sciencesinterannual variabilityMultidisciplinary analysis[SDE.MCG]Environmental Sciences/Global ChangesGlobal warmingrainfall0207 environmental engineeringSST forced responseAfrican Monsoon02 engineering and technologyMonsoon01 natural sciencesSea surface temperatureWest african[ SDE.MCG ] Environmental Sciences/Global Changes13. Climate action[SDU.STU.CL]Sciences of the Universe [physics]/Earth Sciences/ClimatologyClimatologySahelianEnvironmental science[ SDU.STU.CL ] Sciences of the Universe [physics]/Earth Sciences/Climatology020701 environmental engineeringdecadal variability0105 earth and related environmental sciences
researchProduct

Mean Radiant Temperature Measurements through Small Black Globes under Forced Convection Conditions

2021

One of the most critical variables in the field of thermal comfort measurements is the mean radiant temperature which is typically measured with a standard 150 mm black globe thermometer. This is also the reference instrument required for the assessment of heat stress conditions by means of the well-known Wet Bulb Globe Temperature index (WBGT). However, one of the limitations of this method is represented by the relatively long response time. This is why in recent years there has been a more and more pressing need of smart sensors for controlling Heating Ventilation and Air Conditioning (HVAC) systems, and for pocket heat stress meters (e.g., WBGT meters provided with table tennis balls). …

Atmospheric Science010504 meteorology & atmospheric sciencesthermal comfortWet-bulb globe temperature0211 other engineering and technologiesEnclosure02 engineering and technologyEnvironmental Science (miscellaneous)Heat stre01 natural sciencesheat stressmean radiant temperatureMeteorology. ClimatologyHVACRadiative transfer021108 energyMean radiant temperature0105 earth and related environmental sciencesbusiness.industryThermal comfortMechanicsmean radiant temperature; globe temperature; thermal comfort; heat stress; WBGT; Predicted Heat Strain (PHS); smart sensorsForced convectionGlobe temperature; Heat stress; Mean radiant temperature; Predicted Heat Strain (PHS); Smart sensors; Thermal comfort; WBGTSmart sensorPredicted Heat Strain (PHS)Thermometersmart sensorsglobe temperatureEnvironmental scienceQC851-999WBGTbusinessAtmosphere
researchProduct

Compact two-electron wave function for bond dissociation and Van der Waals interactions: A natural amplitude assessment

2014

Electron correlations in molecules can be divided in short range dynamical correlations, long range Van der Waals type interactions and near degeneracy static correlations. In this work we analyze for a one-dimensional model of a two-electron system how these three types of correlations can be incorporated in a simple wave function of restricted functional form consisting of an orbital product multiplied by a single correlation function $f(r_{12})$ depending on the interelectronic distance $r_{12}$. Since the three types of correlations mentioned lead to different signatures in terms of the natural orbital (NO) amplitudes in two-electron systems we make an analysis of the wave function in t…

Atomic Physics (physics.atom-ph)General Physics and AstronomyFOS: Physical sciencesPhysics - Atomic Physicssymbols.namesakeCondensed Matter - Strongly Correlated ElectronsAtomic orbitalQuantum mechanicsPhysics - Chemical PhysicsPhysics::Atomic PhysicsSDG 7 - Affordable and Clean EnergyPhysical and Theoretical ChemistryWave functionAnsatzPhysicsChemical Physics (physics.chem-ph)Quantum Physics/dk/atira/pure/sustainabledevelopmentgoals/affordable_and_clean_energyta114Electronic correlationStrongly Correlated Electrons (cond-mat.str-el)Computational Physics (physics.comp-ph)Diatomic molecule3. Good healthBond lengthAmplitudesymbolsvan der Waals forceQuantum Physics (quant-ph)Physics - Computational Physics
researchProduct

Invasive Observation by Atomic Force Microscope of a Langmuir-Blodgett Monolayer of Gramicidin

2002

The properties of gramicidin, a linear antibiotic polypeptide of 15 amino acids, have been studied at the air-water interface. Analysis of the pressure-area isotherm is not able to conclude about the conformational behavior of gramicidin in the monolayer. Langmuir-Blodgett deposition of gramicidin layers onto a mica substrate has been developed for atomic force microscopy (AFM) observations. At high pressure of deposition, the gramicidin monolayer is composed of dimers perpendicular to the surface. The possibility of removing the half upper part of this dimer monolayer with the AFM tip is more in favor of a structure of single-stranded helical dimers.

Atomic force microscopyDimertechnology industry and agricultureMedicine (miscellaneous)Langmuir–Blodgett filmchemistry.chemical_compoundCrystallographychemistryHigh pressureMonolayerpolycyclic compoundsGramicidinlipids (amino acids peptides and proteins)Mica substrateDeposition (law)Probe Microscopy
researchProduct

Relating morphology to nanoscale mechanical properties: from crystalline to mesomorphic iPP

2005

Atomic force microscopyMechanical characterizationNanoindentation
researchProduct