Policy search for motor primitives in robotics

DOI10.1007/S10994-010-5223-6zbMATH Open1237.68229DBLPjournals/ml/KoberP11OpenAlexW2012392077WikidataQ57539299 ScholiaQ57539299MaRDI QIDQ413874FDOQ413874

Authors: Jens Kober, Jan Peters 

Publication date: 8 May 2012

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10994-010-5223-6

Recommendations

• Imitation and reinforcement learning for motor primitives with perceptual coupling
• A generalized path integral control approach to reinforcement learning
• Reward-weighted regression with sample reuse for direct policy search in reinforcement learning
• Towards motor skill learning for robotics
• Non-parametric policy search with limited information loss

zbMATH Keywords

episodic reinforcement learningmotor controlmotor primitivespolicy learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Artificial intelligence for robotics (68T40)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Adaptive probabilistic networks with hidden variables
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• An introduction to MCMC for machine learning
• Study of the starting pressure gradient in branching network
• Using Expectation-Maximization for Reinforcement Learning
• Control of nonlinear mechanical systems
• Scalable techniques from nonparametric statistics for real time robot learning

Cited In (24)

• Closing the gap: combining task specification and reinforcement learning for compliant vegetable cutting
• End-to-end training of deep visuomotor policies
• Nonconvex policy search using variational inequalities
• Optimal control as a graphical model inference problem
• PI-ELM: reinforcement learning-based adaptable policy improvement for dynamical system
• Non-parametric policy search with limited information loss
• Autonomous reinforcement learning with experience replay
• Model-based policy gradients with parameter-based exploration by least-squares conditional density estimation
• Policy gradient in Lipschitz Markov decision processes
• Learning omnidirectional path following using dimensionality reduction
• Active contextual policy search
• Variational policy search using sparse Gaussian process priors for learning multimodal optimal actions
• Probabilistic inference for determining options in reinforcement learning
• Title not available (Why is that?)
• Theoretical foundation for CMA-ES from information geometry perspective
• Kernel dynamic policy programming: applicable reinforcement learning to robot systems with high dimensional states
• Preference-based reinforcement learning: a formal framework and a policy iteration algorithm
• Dealing with multiple experts and non-stationarity in inverse reinforcement learning: an application to real-life problems
• Model-based contextual policy search for data-efficient generalization of robot skills
• Title not available (Why is that?)
• Towards motor skill learning for robotics
• A generalized path integral control approach to reinforcement learning
• Imitation and reinforcement learning for motor primitives with perceptual coupling
• Reinforcement learning algorithms with function approximation: recent advances and applications

This page was built for publication: Policy search for motor primitives in robotics

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q413874)