A Reinforcement Learning Algorithm With Evolving Fuzzy Neural Networks

Authors: ,

Abstract: The synergy of the two paradigms, neural network and fuzzy inference system, has given rise to rapidly emerging filed, neuro-fuzzy systems. Evolving neuro-fuzzy systems are intended to use online learning to extract knowledge from data and perform a high-level adaptation of the network structure. We explore the potential of evolving neuro-fuzzy systems in reinforcement learning (RL) applications. In this paper, a novel on-line sequential learning evolving neuro-fuzzy model design for RL is proposed. We develop a dynamic evolving fuzzy neural network (DENFIS) function approximation approach to RL systems. Potential of this approach is demonstrated through a case study⎯two-link robot manipulator. Simulation results have demonstrated that the proposed approach performs well in reinforcement learning problems.

International Journal of Electrical Engineering and Computer Science, E-ISSN: 2769-2507, Volume 2, 2020, Art. #12

PDF
XML
Cite
×
Citation Tools
WSEAS AMA
Hitesh Shah, M.Gopal, "A Reinforcement Learning Algorithm With Evolving Fuzzy Neural Networks," International Journal of Electrical Engineering and Computer Science, vol. 2, pp. 68-72, 2020, DOI:
Hitesh Shah, M.Gopal. A Reinforcement Learning Algorithm With Evolving Fuzzy Neural Networks. International Journal of Electrical Engineering and Computer Science. 2020;2:68-72.
Copy to Clipboard
Citation copied to Clipboard

Certification

---