Symbolic structures in numeric reinforcement for learning optimum robot trajectory

DOI10.1016/S0921-8890(01)00142-7MaRDI QIDQ4538401zbMATH OpenFDO

Authors

Publication date 14 July 2002

Published in Robotics and Autonomous Systems (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/S0921-8890(01)00142-7

zbMATH Keywords

domain knowledgefuzzy behaviornumeric reinforcementradial basis functions

Mathematics Subject Classification ID

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

Recommendations

• Multistrategy learning for robot behaviours
• Robot control optimization using reinforcement learning
• scientific article; zbMATH DE number 918072
• Module-based reinforcement learning: Experiments with a real robot
• scientific article; zbMATH DE number 1728771

Cited in

(4)

• Gradient-based mixed planning with symbolic and numeric action parameters
• Symbolic exploitation of symmetry in numerical pathfollowing
• Multistrategy learning for robot behaviours
• Detecting and exploiting symmetry to accelerate reinforcement learning

This page was built for publication: Symbolic structures in numeric reinforcement for learning optimum robot trajectory

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4538401)