Detecting and exploiting symmetry to accelerate reinforcement learning

DOI10.1137/1.9781611977745.14zbMATH Open1545.93475MaRDI QIDQ6567655FDOQ6567655

Authors: Ashish Pujari, Haoze Lin, William Liles Neal, Tony Dear, Scott David Kelly 

Publication date: 5 July 2024

Recommendations

• Symbolic structures in numeric reinforcement for learning optimum robot trajectory
• Reinforcement learning control of unknown dynamic systems
• Dimension reduction and its application to model-based exploration in continuous spaces
• Scalable transfer learning in heterogeneous, dynamic environments
• Adaptive optimal output tracking of continuous-time systems via output-feedback-based reinforcement learning

Mathematics Subject Classification ID

Agent technology and artificial intelligence (68T42) Automated systems (robots, etc.) in control theory (93C85)

This page was built for publication: Detecting and exploiting symmetry to accelerate reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6567655)