Policy search for motor primitives in robotics

DOI10.1007/s10994-010-5223-6zbMath1237.68229OpenAlexW2012392077WikidataQ57539299 ScholiaQ57539299MaRDI QIDQ413874

Jan Peters, Jens Kober

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

zbMATH Keywords

motor controlepisodic reinforcement learningmotor primitivespolicy learning

Mathematics Subject Classification ID

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

Related Items

Probabilistic inference for determining options in reinforcement learning, Model-based policy gradients with parameter-based exploration by least-squares conditional density estimation, Unnamed Item, Optimal control as a graphical model inference problem, Reinforcement learning algorithms with function approximation: recent advances and applications, Preference-based reinforcement learning: a formal framework and a policy iteration algorithm, Theoretical foundation for CMA-ES from information geometry perspective, Nonconvex Policy Search Using Variational Inequalities, Autonomous reinforcement learning with experience replay, Policy gradient in Lipschitz Markov decision processes, Dealing with multiple experts and non-stationarity in inverse reinforcement learning: an application to real-life problems, Closing the gap: combining task specification and reinforcement learning for compliant vegetable cutting

Cites Work

• Unnamed Item
• Unnamed Item
• Study of the starting pressure gradient in branching network
• Scalable techniques from nonparametric statistics for real time robot learning
• Adaptive probabilistic networks with hidden variables
• An introduction to MCMC for machine learning
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Control of nonlinear mechanical systems
• Using Expectation-Maximization for Reinforcement Learning