Closed-loop learning of visual control policies

MaRDI QIDQ3624057zbMATH OpenFDO

Authors S. R. Jodogne, Justus Piater

Publication date 28 April 2009

Full work available at URL https://arxiv.org/abs/1110.2210

zbMATH Keywords

greedy algorithmreinforcement learning algorithm

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10) Computing methodologies for image processing (68U10) Nonnumerical algorithms (68W05)

Recommendations

• Learning visual representations for interactive systems
• End-to-end training of deep visuomotor policies
• Perception control
• A generalized path integral control approach to reinforcement learning
• Imitation and reinforcement learning for motor primitives with perceptual coupling

Cited in

(4)

• Perception control
• End-to-end training of deep visuomotor policies
• Learning visual representations for interactive systems
• Closed-loop deep learning: generating forward models with backpropagation

This page was built for publication: Closed-loop learning of visual control policies

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3624057)