Reinforcement learning with via-point representation

DOI10.1016/J.NEUNET.2003.11.004MaRDI QIDQ1883866zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Hiroyuki Miyamoto, Jun Morimoto, Kenji Doya, Mitsuo Kawato

Publication date 14 October 2004

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2003.11.004

zbMATH Keywords

Cart-poleHierarchical reinforcement learningMotor controlRoboticsSwing upVia-point

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Control/observation systems involving computers (process control, etc.) (93C83) Automated systems (robots, etc.) in control theory (93C85)

Recommendations

• A generalized path integral control approach to reinforcement learning
• Learning movement sequences with a delayed reward signal in a hierarchical model of motor function
• Acquisition of stand-up behavior by a real robot using hierarchical reinforcement learning
• A reinforcement learning adaptive fuzzy controller for robots.
• Robot motor skill acquisition with alternate learning in two spaces

Cites work

• Reinforcement learning. An introduction

Cited in

(2)

• Learning and control of exploration primitives
• Acquisition of stand-up behavior by a real robot using hierarchical reinforcement learning

This page was built for publication: Reinforcement learning with via-point representation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1883866)