https://axon.cs.byu.edu/~martinez/classes/678/Presentations/Yao.pdf

Extreme learning machine: Theory and applications

I have developed "tennis elbow" from lugging this book around the past four weeks, but it is worth the pain, the effort, and the aspirin. It is also worth the (relatively speaking) bargain price. Including appendixes, this book contains 894 pages of text. The entire panorama of the neural sciences is surveyed and examined, and it is comprehensive in its scope, from genomes to social behaviors. The editors explicitly state that the book is designed as "an introductory text for students of biology, behavior, and medicine," but it is hard to imagine any audience, interested in any fragment of neuroscience at any level of sophistication, that would not enjoy this book. The editors have done a masterful job of weaving together the biologic, the behavioral, and the clinical sciences into a single tapestry in which everyone from the molecular biologist to the practicing psychiatrist can find and appreciate his or

Principles of Neural Science

This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the field and a broad selection of current work are summarized. Reinforcement learning is the problem faced by an agent that learns behavior through trial-and-error interactions with a dynamic environment. The work described here has a resemblance to work in psychology, but differs considerably in the details and in the use of the word "reinforcement." The paper discusses central issues of reinforcement learning, including trading off exploration and exploitation, establishing the foundations of the field via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state. It concludes with a survey of some implemented systems and an assessment of the practical utility of current methods for reinforcement learning.

/pdf/reinforcement-learning-a-survey-38lmyylg2y.pdf

Reinforcement learning: a survey

Planning algorithms are impacting technical disciplines and industries around the world, including robotics, computer-aided design, manufacturing, computer graphics, aerospace applications, drug design, and protein folding. This coherent and comprehensive book unifies material from several sources, including robotics, control theory, artificial intelligence, and algorithms. The treatment is centered on robot motion planning but integrates material on planning in discrete spaces. A major part of the book is devoted to planning under uncertainty, including decision theory, Markov decision processes, and information spaces, which are the “configuration spaces” of all sensor-based planning problems. The last part of the book delves into planning under differential constraints that arise when automating the motions of virtually any mechanical system. Developed from courses taught by the author, the book is intended for students, engineers, and researchers in robotics, artificial intelligence, and control theory as well as computer graphics, algorithms, and computational biology.

Planning Algorithms: Introductory Material

This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the field and a broad selection of current work are summarized. Reinforcement learning is the problem faced by an agent that learns behavior through trial-and-error interactions with a dynamic environment. The work described here has a resemblance to work in psychology, but differs considerably in the details and in the use of the word ``reinforcement.'' The paper discusses central issues of reinforcement learning, including trading off exploration and exploitation, establishing the foundations of the field via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state. It concludes with a survey of some implemented systems and an assessment of the practical utility of current methods for reinforcement learning.

Reinforcement Learning: A Survey

Stochastic robustness synthesis is used to evaluate compensator robustness numerically and to automate the design of stochastic optimal controllers. Monte Carlo simulation (MCS) is applied to quantify robustness, and a genetic algorithm (GA) searches for the optimal controller. The overall algorithm is computationally expensive, and parallel computing is utilized to reduce execution times. Parallel stochastic robustness analysis and design (PSRAD) is introduced as a viable solution for real-time controller design. A dynamic scheduler is proposed to alleviate stochastic load imbalances. Results are presented for a shared-virtual-memory computer.

Parallel stochastic robustness synthesis for control system design

A system identification model that combines generalized-spline function approximation with a nonlinear control system is described. The complete control system contains three main elements: a nonlinear-inverse-dynamic control law that depends on a comprehensive model of the plant, a state estimator whose outputs drive the control law, and a function approximation scheme that models the system dynamics. The system-identification task, which combines an extended Kalman filter with a function approximator modeled here as an artificial neural network, is considered in detail. The state estimator provides the necessary data so that continuous training of the neural network is possible during normal operation. The results of an application of the identification techniques to a nonlinear transport aircraft model are presented.

A System Identification Model for Adaptive Nonlinear Control

Quantitative knowledge acquisition for expert systems

A method of designing a family of robust compensators is presented. Each compensator's transfer function is found using a genetic-algorithm search for numerator and denominator coefficients that minimize the probability of unsatisfactory stability and performance, subject to uncertainty in the real parameters of the plant. As the search progresses, probabilities are estimated by Monte Carlo evaluation of stability and performance criteria. The design procedure employs a sweep from the lowest feasible transfer-function order to higher order, terminating either when design goals have been achieved or when no further improvement is evident. The study illustrates the evolution of pole and zero locations as compensator order increases for a benchmark problem in which settling-time and control-usage performance criteria must be satisfied subject to minimum likelihood of instability. The method provides a means for estimating the best possible compensation of a given order based on repeated searches.

Searching for robust minimal-order compensators

This paper describes a general-aviation digital avionics flight-test facility being jointly developed by the Flight Dynamics Laboratory of Princeton University and NASA/Langley Research Center. This facility consists of the Princeton avionics research aircraft (ARA) and NASA/Langley's digital avionics research (DARE) system. The ARA is a fully instrumented five-degree-of-freedom fly-by-wire aircraft. The DARE system contains a state-of-the-art flight computer system and receiving equipment that permits use of the NASA/Wallops Flight Center's position-tracking ground-based display-generation and ground-to-air digital-data-link equipment. The DARE/ARA system will be used for flight evaluation of advanced control, guidance, and display concepts developed as part of NASA/Langley Research Center's general aviation terminal area operations program.

Robert F. Stengel

Papers

Parallel stochastic robustness synthesis for control system design

A System Identification Model for Adaptive Nonlinear Control

Quantitative knowledge acquisition for expert systems

Searching for robust minimal-order compensators

NASA/Princeton digital avionics flight test facility