Model-based reinforcement learning

Results 81 to 90 of about 37,169,246 (294)

Consistency of fuzzy model-based reinforcement learning [PDF]

2008 IEEE International Conference on Fuzzy Systems (IEEE World Congress on Computational Intelligence), 2008
Reinforcement learning (RL) is a widely used paradigm for learning control. Computing exact RL solutions is generally only possible when process states and control actions take values in a small discrete set. In practice, approximate algorithms are necessary.
Lucian Busoniu +3 more
openaire +2 more sources

Deep Learning Pose Estimation for Phenotyping of Co‐Occurring Hyperkinetic Movement Disorders

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Objective To explore whether routine outpatient video combined with deep learning‐based pose estimation and clinically interpretable kinematic features can support multi‐label phenotyping of co‐occurring hyperkinetic movement disorders (HMDs).
Laura Cif +17 more
wiley +1 more source

Application of deep reinforcement learning in the design and optimization of English continuing education teaching content

Discover Artificial Intelligence
This study discusses the application of deep reinforcement learning in the design and optimization of English continuing education teaching content. Aiming at the one-size-fits-all problem in the traditional education model, it puts forward personalized ...
Jinfeng Ma
doaj +1 more source

CSF Cytokine Network Organization Predicts Progression Independent of Relapse and MRI Activity in Multiple Sclerosis

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Objective Progression independent of relapse activity is a major determinant of long‐term disability in multiple sclerosis, but its immunopathologic basis remains incompletely understood. We investigated whether relapse‐independent progression in radiologically stable relapsing–remitting multiple sclerosis is associated with distinct ...
Antonio Bruno +19 more
wiley +1 more source

Transferring Instances for Model-Based Reinforcement Learning [PDF]

, 2008
Reinforcement learningagents typically require a significant amount of data before performing well on complex tasks. Transfer learningmethods have made progress reducing sample complexity, but they have primarily been applied to model-free learning methods, not more data-efficient model-based learning methods.
Matthew E. Taylor, Nicholas K. Jong, Peter Stone 0001 +2 more
openaire +2 more sources

Multi-model based reinforcement learning and application

, 2020
Decker, Keith S.Reinforcement learning (RL) as a category of machine learning methods learns sequential decision-making policies by interacting with the environment and maximizing a cumulative reward.
Wei, Haoran
core +1 more source

Boundary‐Dependent Sleep–Wake Dysregulation in Idiopathic Hypersomnia

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Objective Idiopathic hypersomnia (IH) presents with excessive daytime sleepiness (EDS) despite apparently preserved nocturnal sleep, challenging traditional models of hypersomnolence based on sleep loss or fragmentation. We aimed to test the hypothesis that EDS in IH reflects excessive stabilization of the sleep state, consistent with ...
Samantha Mombelli +13 more
wiley +1 more source

Model-based Adversarial Meta-Reinforcement Learning

CoRR, 2020
Meta-reinforcement learning (meta-RL) aims to learn from multiple training tasks the ability to adapt efficiently to unseen test tasks. Despite the success, existing meta-RL algorithms are known to be sensitive to the task distribution shift. When the test task distribution is different from the training task distribution, the performance may degrade ...
Zichuan Lin +3 more
openaire +4 more sources

Axial Function Reflects Global Severity in Inherited Ataxias: The Upright Stability Score in Ambulatory Friedreich vs. Spinocerebellar Ataxia

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Objective Inherited ataxias are clinically diverse neurodegenerative diseases, complicating the choice of outcome measures for trials. In spinocerebellar ataxia (SCA), regulatory concerns about the Scale for the Assessment and Rating of Ataxia (SARA) caused a shift toward functional SARA (f‐SARA), contributing to pivotal trial failure.
Christian Rummey +52 more
wiley +1 more source

Data-Efficient Reinforcement Learning Framework for Autonomous Flight Based on Real-World Flight Data

Drones
Recently, autonomous flight has emerged as a key technology in the aerospace and defense sectors; however, traditional code-based autonomous flight systems face limitations in complex environments.
Uicheon Lee, Seonah Lee, Kyonghoon Kim
doaj +1 more source

reinforcement learning
deep reinforcement learning
machine learning