Task-specific loss: a teacher-centered approach to transfer learning between distinctly structured robotic agents

DOI10.1007/978-3-030-92442-3_10MaRDI QIDQ2101736zbMATH OpenOpenAlexFDO

Authors Mehdi Mounsif, Sébastien Lengagne, Benoit Thuilot, Lounis Adouane

Publication date 6 December 2022

Full work available at URL https://doi.org/10.1007/978-3-030-92442-3_10

zbMATH Keywords

controldifferentiable modelsgenerative adversarial networkstransfer learningvariational autoencoders

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Automated systems (robots, etc.) in control theory (93C85)

Recommendations

• Robot control policy transfer based on progressive neural network
• Towards motor skill learning for robotics
• Abstraction in data-sparse task transfer
• scientific article; zbMATH DE number 7112142
• Transfer learning for reinforcement learning domains: a survey

Cites work

• Task-specific loss: a teacher-centered approach to transfer learning between distinctly structured robotic agents

Cited in

(4)

• Task-specific loss: a teacher-centered approach to transfer learning between distinctly structured robotic agents
• Abstraction in data-sparse task transfer
• Transferring skills to humanoid robots by extracting semantic representations from observations of human activities
• Robot control policy transfer based on progressive neural network

Describes a project that uses

Uses Software

• AlexNet
• ALBERT
• Faster R-CNN
• Transformer-XL
• U-Net
• ImageNet
• BERT
• DeepLoco
• Adam
• YOLO
• CamemBERT
• GitHub

This page was built for publication: Task-specific loss: a teacher-centered approach to transfer learning between distinctly structured robotic agents

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2101736)