L
Larry D. Pyeatt
Researcher at South Dakota School of Mines and Technology
Publications - 40
Citations - 797
Larry D. Pyeatt is an academic researcher from South Dakota School of Mines and Technology. The author has contributed to research in topics: Reinforcement learning & Partially observable Markov decision process. The author has an hindex of 12, co-authored 39 publications receiving 758 citations. Previous affiliations of Larry D. Pyeatt include Texaco & Colorado State University.
Papers
More filters
A comparison between cellular encoding and direct encoding for genetic neural networks
TL;DR: This paper compares the efficiency of two encoding schemes for Artificial Neural Networks optimized by evolutionary algorithms and solves a more difficult problem: balancing two poles when no information about the velocity is provided as input.
Decision Tree Function Approximation in Reinforcement Learning
Larry D. Pyeatt,Adele E. Howe +1 more
TL;DR: This work presents a decision tree based approach to function approximation in reinforcement learning and finds that the decision tree can provide better learning performance than the neural network function approximation and can solve large problems that are infeasible using table lookup.
Patent
Interpretation of fluorescence fingerprints of crude oils and other hydrocarbon mixtures using neural networks
Marilyn V. Reyes,Larry D. Pyeatt +1 more
Abstract: An artificial intelligence system is used with a conglomeration of fluorescence data to provide a method of improving recognition of an unknown from its spectral pattern. Customized neural network systems allow the ultimate organization and resourceful use of assumption-free variables already existing in a total scanning fluorescence database for a much more comprehensive, discrete and accurate differentiation and matching of spectra than is possible with human memory. The invention provides increased speed of fingerprinting analysis, accuracy and reliability together with a decreased learning curve and heightened objectivity for the analysis.
Journal Article
Reinforcement learning for closed-loop propofol anesthesia: a study in human volunteers
Brett L. Moore,Larry D. Pyeatt,Vivekanand Kulkarni,Periklis Panousis,Kevin A. Padrez,Anthony G. Doufas +5 more
TL;DR: Investigation of Reinforcement learning's application in the delivery of patient-specific, propofol-induced hypnosis in human volunteers suggests that RL may be considered a viable alternative for solving other difficult closed-loop control problems in medicine.
Proceedings Article
Cellular Encoding Applied to Neurocontrol
TL;DR: The learning times and generalization capabilities are compared for neural networks developed using both methods and architectures with no hidden units were produced for the single pole and the two pole problem when velocity information is supplied as an input.