Reinforcement learning endowed with safe veto policies to learn the control of linked-multicomponent robotic systems

DOI10.1016/J.INS.2015.04.005zbMATH Open1390.68691OpenAlexW1985215440MaRDI QIDQ1749908FDOQ1749908

Authors: Borja Fernandez-Gauna, Manuel Graña, Jose Manuel Lopez-Guede, Ismael Etxeberria-Agiriano, Igor Ansoategui 

Publication date: 17 May 2018

Published in: Information Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.ins.2015.04.005

Recommendations

• Undesired state-action prediction in multi-agent reinforcement learning for linked multi-component robotic system control
• Safe Exploration of State and Action Spaces in Reinforcement Learning
• A comprehensive survey on safe reinforcement learning
• Safe reinforcement learning for continuous spaces through Lyapunov-constrained behavior
• Reinforcement learning control of constrained dynamic systems with uniformly ultimate boundedness stability guarantee

zbMATH Keywords

reinforcement learninglinked multicomponent robotic systemssafe exploration policiesspeeding convergence of RL

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Artificial intelligence for robotics (68T40) Automated systems (robots, etc.) in control theory (93C85)

Cites Work

• \({\mathcal Q}\)-learning
• Title not available (Why is that?)
• Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
• Title not available (Why is that?)
• Reinforcement learning algorithms with function approximation: recent advances and applications
• Undesired state-action prediction in multi-agent reinforcement learning for linked multi-component robotic system control
• Title not available (Why is that?)
• Machine Learning: ECML 2004
• Title not available (Why is that?)

Cited In (3)

• Safe reward‐based deep reinforcement learning control for an electro‐hydraulic servo system
• Undesired state-action prediction in multi-agent reinforcement learning for linked multi-component robotic system control
• A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems

Uses Software

• Approxrl

This page was built for publication: Reinforcement learning endowed with safe veto policies to learn the control of linked-multicomponent robotic systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1749908)