NASA NTRS · 19960022772
Using Fuzzy Logic for Performance Evaluation in Reinforcement Learning
Abstract
Current reinforcement learning algorithms require long training periods which generally limit their applicability to small size problems. A new architecture is described which uses fuzzy rules to initialize its two neural networks: a neural network for performance evaluation and another for action selection. This architecture is applied to control of dynamic systems and it is demonstrated that it is possible to start with an approximate prior knowledge and learn to refine it through experiments using reinforcement learning.
Keep this discovery
Explore connections, maps & timelines
Berenji, Hamid R., Khedkar, Pratap S.. 1992-01-01. Using Fuzzy Logic for Performance Evaluation in Reinforcement Learning. https://searchnasa.com/record/nasa%3A19960022772/using-fuzzy-logic-for-performance-evaluation-in-reinforcement-learning
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Search NASA by Indiciae: BibTeX · RIS.