SEARCH · Search NASA

Results for “Learning”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 217 records · Page 12

All sources NASA NTRS DOE OSTI

DOE OSTI2026

Adaptive Cybersecurity for Distributed Energy Resources (AdCyDER): Online Reinforcement Learning with Stackelberg-Optimized Defenses — Pipeline Architecture, Evaluation Methodology, and Findings from a Synthetic-Data Evaluation

This report documents the design and evaluation of an integrated online-learning pipeline developed within the AdCyDER project for Distributed Energy Resource (DER) cybersecurity. The pipeline couples a Reinforcement Learning (RL) attack classifier — which produces an attack-type probability distribution — with a Stackelberg game-theoretic (GT) defense selector that consumes those distributions alongside SME-encoded priors over (defense, attack) effectiveness pairings and perdefense costs to choose grid-health-preserving defenses. The objective is not attack classification per se but production of distributions that drive effective defense selection through the Stackelberg layer, learned from delayed grid-health feedback rather than labeled attack data. AdCyDER as a whole is broader than the work presented here; this report covers the specific RL/GT loop integration and its evaluation. We present the integrated pipeline (SCADA telemetry with Fronius inverter physics, Suricata IDS, time-windowed aggregation, per-facility LSTM classifier, Stackelberg optimizer, OpenC2 actuators), an experimental campaign of 28 eight-hour iterations across three baseline modes, and a pipeline-ordered diagnostic protocol. The protocol identifies two distinct failure modes within the loop: paired supervised ceilings on the same features establish that the deployed online RL classifier (macro F1 ≈ 0.07) sits at least 4.7× below a same-architecture supervised LSTM (≈ 0.34) and 10–11× below a linear feature-signal ceiling (≈ 0.70–0.79 depending on per-facility isolation), localizing the dominant failure to the training procedure; and the reward signal driving online updates carries weak directional coupling with classifier correctness in the methodology-expected direction (multi-lens convergent: top-decile P(true) records produce more frequent state changes and slightly larger improvements, top-vs-bot Cohen’s 𝑑 ≈ −0.19), but at effect magnitudes too small to drive gradient-based learning at the campaign sample size. The original learning hypothesis is not supported by the data. The primary contributions are the diagnostic methodology — proposed as a transferable falsification protocol for online RL/GT defense pipelines learning from delayed environmental reward — and the open, reproducible experimental infrastructure. We outline reward reformulation as the highest-priority aspirational next step given the underpowered-but-aligned Q6 reading, with hardware-in-the-loop evaluation as the broadest scope-expansion option.

Blakely, Benjamin [Argonne National Laboratory (AN↗

NASA NTRS1987

Optoelectronic analogs of self-programming neural nets - Architecture and methodologies for implementing fast stochastic learning by simulated annealing

Self-organization and learning is a distinctive feature of neural nets and processors that sets them apart from conventional approaches to signal processing. It leads to self-programmability which alleviates the problem of programming complexity in artificial neural nets. In this paper architectures for partitioning an optoelectronic analog of a neural net into distinct layers with prescribed interconnectivity pattern to enable stochastic learning by simulated annealing in the context of a Boltzmann machine are presented. Stochastic learning is of interest because of its relevance to the role of noise in biological neural nets. Practical considerations and methodologies for appreciably accelerating stochastic learning in such a multilayered net are described. These include the use of parallel optical computing of the global energy of the net, the use of fast nonvolatile programmable spatial light modulators to realize fast plasticity, optical generation of random number arrays, and an adaptive noisy thresholding scheme that also makes stochastic learning more biologically plausible. The findings reported predict optoelectronic chips that can be used in the realization of optical learning machines.

Farhat, Nabil H.↗

NASA NTRS1988

Learning dominance relations in combinatorial search problems

Dominance relations commonly are used to prune unnecessary nodes in search graphs, but they are problem-dependent and cannot be derived by a general procedure. The authors identify machine learning of dominance relations and the applicable learning mechanisms. A study of learning dominance relations using learning by experimentation is described. This system has been able to learn dominance relations for the 0/1-knapsack problem, an inventory problem, the reliability-by-replication problem, the two-machine flow shop problem, a number of single-machine scheduling problems, and a two-machine scheduling problem. It is considered that the same methodology can be extended to learn dominance relations in general.

Yu, Chee-Fen↗

NASA NTRS1990

Rule-based mechanisms of learning for intelligent adaptive flight control

How certain aspects of human learning can be used to characterize learning in intelligent adaptive control systems is investigated. Reflexive and declarative memory and learning are described. It is shown that model-based systems-theoretic adaptive control methods exhibit attributes of reflexive learning, whereas the problem-solving capabilities of knowledge-based systems of artificial intelligence are naturally suited for implementing declarative learning. Issues related to learning in knowledge-based control systems are addressed, with particular attention given to rule-based systems. A mechanism for real-time rule-based knowledge acquisition is suggested, and utilization of this mechanism within the context of failure diagnosis for fault-tolerant flight control is demonstrated.

Handelman, David A.↗

NASA NTRS1989

Learning control for slewing of a flexible panel

This paper studies the applicability of a discrete-time learning control method to the slewing control of a large flexible panel. Among the issues discussed are feasibility of the desired trajectories and their specification schemes, learning control by linear feedback, limitation of the actuator device output, and robustness to parameter changes or modeling errors associated with the chosen learning control design. To demonstrate the effectiveness of learning control, the system is designed with a proportional controller of the base angle only. Then application of the learning control is shown to make the system learn quickly to achieve the desired slewing without residual vibration at the end of the maneuver. Simulation results are reported and discussed.

Phan, M.↗

NASA NTRS1990

Analytical learning and term-rewriting systems

Analytical learning is a set of machine learning techniques for revising the representation of a theory based on a small set of examples of that theory. When the representation of the theory is correct and complete but perhaps inefficient, an important objective of such analysis is to improve the computational efficiency of the representation. Several algorithms with this purpose have been suggested, most of which are closely tied to a first order logical language and are variants of goal regression, such as the familiar explanation based generalization (EBG) procedure. But because predicate calculus is a poor representation for some domains, these learning algorithms are extended to apply to other computational models. It is shown that the goal regression technique applies to a large family of programming languages, all based on a kind of term rewriting system. Included in this family are three language families of importance to artificial intelligence: logic programming, such as Prolog; lambda calculus, such as LISP; and combinatorial based languages, such as FP. A new analytical learning algorithm, AL-2, is exhibited that learns from success but is otherwise quite different from EBG. These results suggest that term rewriting systems are a good framework for analytical learning research in general, and that further research should be directed toward developing new techniques.

Laird, Philip↗

NASA NTRS1992

Linear decentralized learning control

The new field of learning control develops controllers that learn to improve their performance at executing a given task, based on experience performing this task. The simplest forms of learning control are based on the same concept as integral control, but operating in the domain of the repetitions of the task. This paper studies the use of such controllers in a decentralized system, such as a robot with the controller for each link acting independently. The basic result of the paper is to show that stability of the learning controllers for all subsystems when the coupling between subsystems is turned off, assures stability of the decentralized learning in the coupled system, provided that the sample time in the digital learning controller is sufficiently short.

Lee, Soo C.↗

NASA NTRS1993

Indirect learning control for nonlinear dynamical systems

In a previous paper, learning control algorithms were developed based on adaptive control ideas for linear time variant systems. The learning control methods were shown to have certain advantages over their adaptive control counterparts, such as the ability to produce zero tracking error in time varying systems, and the ability to eliminate repetitive disturbances. In recent years, certain adaptive control algorithms have been developed for multi-body dynamic systems such as robots, with global guaranteed convergence to zero tracking error for the nonlinear system euations. In this paper we study the relationship between such adaptive control methods designed for this specific class of nonlinear systems, and the learning control problem for such systems, seeking to converge to zero tracking error in following a specific command repeatedly, starting from the same initial conditions each time. The extension of these methods from the adaptive control problem to the learning control problem is seen to be trivial. The advantages and disadvantages of using learning control based on such adaptive control concepts for nonlinear systems, and the use of other currently available learning control algorithms are discussed.

Ryu, Yeong Soon↗

NASA NTRS1995

Development of Distant Learning Laboratory and Creation of Educational Materials

The Office of Education's fundamental goal is to disseminate information, mostly that which relates to science and technology. In this attempt, as I have observed, the office has many programs bringing both students and teachers to NASA Langley to expose them to the facilities and to teach them some about the scientific theory and about available modern technology. As a way of expanding the audience that can be reached, as the expense of bringing people in is limiting, Marchelle Canright has proposed establishing a center dedicated to researching and producing distant learning videos. Although distant learning through telecommunications is not a new concept, as many universities, colleges, and precollege level schools offer televised courses, the research in this field has been limited. Many of the standing distant learning broadcasts are simply recordings of teachers in classrooms giving lectures to their own students; they are not aimed at the television audience. In some cases the videos are produced without a Live-lecture atmosphere, but are still only classroom lectures. In either case, however, the full range of capabilities of video production are not being fully utilized. Methods for best relaying educational material have not been explored. Possibilities for including computerized images and video clips for the purpose of showing diagrams and processes, as well as examples in fitting cases, may add considerably to the educational value of these videos. Also, through Internet and satellite links, it is possible for remote students to interact with the teachers during televised sessions. These possibilities might, also, add to the effectiveness of distant learning programs. Ms. Canright's proposed center will be dedicated to researching these possibilities and eventually spreading the results to distant learning program managers. This is the project I was involved in over the summer. As implied, the center is still at the foundation stages. Ms. Canright has proposed four or five possible series that could be developed, each one aimed at a specific age group of students, or group of teachers. I was involved in the design of the series aimed at the youngest children, the Picture Book Science series. My involvement included proposing and researching topics, writing a lesson for the first show, writing the latter portion of the picture book story (the part including the scientific lesson), and illustrating the story. I also designed and collected the materials for the Learning Center's television studio set as well as finished the painting of the main backdrop panels.

Considine, Michelle↗

NASA NTRS1995

Emergence of Relations and the Essence of Learning: A Review of Sidman's Equivalence Relations and Behavior: A Research Story

Sidman addresses two very important questions in Equivalence Relations and Behavior: A Research Story: What are the bases of behavioral competence? And how do units of learning become related? The book recounts the story of how an understanding of emergent relations and competencies was achieved through studies in his teaching-research program with mentally retarded subjects. Although children normally accrue vast networks of relations between stimuli and events, those with mental retardation typically do not. Consequently, by learning how to establish those networks, Sidman and his students contribute richly both to the cultivation of competencies by their subjects and, more generally, to an understanding of real-world human behavior. The basic equivalence paradigm affords the subject feedback and reinforcement for very specific choices during training, but the test is not for those choices! Rather, tests for equivalence look for new choices, ones seemingly quite foreign to the training regimen. The tests for equivalence relations entail presentations of stimuli that were the options for conditional choice during reinforced training. In tests of equivalence, correct choices are novel; hence, they have never been reinforced during training. The study of equivalence relations can encourage the emergence of new perspectives that are more symbiotic than competitive. In full acknowledgment of the important role and contributions made by those who identify themselves as experimental analysts of behavior, it is timely that rapprochements be worked toward, as indeed they are, to meld that perspective with others of our time. Both our research methods and our expectations about the nature of the learning process and the abilities of our subjects can delimit what they might learn and what we, in turn, learn about their learning. The text will be of great value for instruction at the upper-division and graduate levels. Its impact will be substantial, for it defines an important advance in our efforts to understand the richness of behavior in both humans and nonhuman animals. Although not presented to that end, the book might also serve to bridge communications with other groups of animal researchers whose interests lie more in a comparative or ethological framework.

Rumbaugh, Duane M.↗

NASA NTRS1999

Cooperation and Coordination Between Fuzzy Reinforcement Learning Agents in Continuous State Partially Observable Markov Decision Processes

Successful operations of future multi-agent intelligent systems require efficient cooperation schemes between agents sharing learning experiences. We consider a pseudo-realistic world in which one or more opportunities appear and disappear in random locations. Agents use fuzzy reinforcement learning to learn which opportunities are most worthy of pursuing based on their promise rewards, expected lifetimes, path lengths and expected path costs. We show that this world is partially observable because the history of an agent influences the distribution of its future states. We consider a cooperation mechanism in which agents share experience by using and-updating one joint behavior policy. We also implement a coordination mechanism for allocating opportunities to different agents in the same world. Our results demonstrate that K cooperative agents each learning in a separate world over N time steps outperform K independent agents each learning in a separate world over K*N time steps, with this result becoming more pronounced as the degree of partial observability in the environment increases. We also show that cooperation between agents learning in the same world decreases performance with respect to independent agents. Since cooperation reduces diversity between agents, we conclude that diversity is a key parameter in the trade off between maximizing utility from cooperation when diversity is low and maximizing utility from competitive coordination when diversity is high.

Berenji, Hamid R.↗

NASA NTRS2001

Learning Styles of Pilots Currently Qualified in United States Air Force Aircraft

Kolb's Learning Style Inventory was used to identify the predominant learning styles of pilots currently qualified in United States Air Force aircraft. The results indicate that these pilots show a significant preference for facts and things over people and feelings. By understanding the preferred learning styles of the target population, course material can be developed that take advantage of the strengths of these learning styles. This information can be especially useful in the future design of cockpit resource management training. The training program can be developed to demonstrate both that there are different learning styles and that it is possible to take advantage of the relative strengths of each of these learning styles.

Kanske, Craig A.↗

NASA NTRS1996

The cerebellum: a neuronal learning machine?

Comparison of two seemingly quite different behaviors yields a surprisingly consistent picture of the role of the cerebellum in motor learning. Behavioral and physiological data about classical conditioning of the eyelid response and motor learning in the vestibulo-ocular reflex suggests that (i) plasticity is distributed between the cerebellar cortex and the deep cerebellar nuclei; (ii) the cerebellar cortex plays a special role in learning the timing of movement; and (iii) the cerebellar cortex guides learning in the deep nuclei, which may allow learning to be transferred from the cortex to the deep nuclei. Because many of the similarities in the data from the two systems typify general features of cerebellar organization, the cerebellar mechanisms of learning in these two systems may represent principles that apply to many motor systems.

Non-NASA Center↗

NASA NTRS2004

Learning to Control Advanced Life Support Systems

Advanced life support systems have many interacting processes and limited resources. Controlling and optimizing advanced life support systems presents unique challenges. In particular, advanced life support systems are nonlinear coupled dynamical systems and it is difficult for humans to take all interactions into account to design an effective control strategy. In this project. we developed several reinforcement learning controllers that actively explore the space of possible control strategies, guided by rewards from a user specified long term objective function. We evaluated these controllers using a discrete event simulation of an advanced life support system. This simulation, called BioSim, designed by Nasa scientists David Kortenkamp and Scott Bell has multiple, interacting life support modules including crew, food production, air revitalization, water recovery, solid waste incineration and power. They are implemented in a consumer/producer relationship in which certain modules produce resources that are consumed by other modules. Stores hold resources between modules. Control of this simulation is via adjusting flows of resources between modules and into/out of stores. We developed adaptive algorithms that control the flow of resources in BioSim. Our learning algorithms discovered several ingenious strategies for maximizing mission length by controlling the air and water recycling systems as well as crop planting schedules. By exploiting non-linearities in the overall system dynamics, the learned controllers easily out- performed controllers written by human experts. In sum, we accomplished three goals. We (1) developed foundations for learning models of coupled dynamical systems by active exploration of the state space, (2) developed and tested algorithms that learn to efficiently control air and water recycling processes as well as crop scheduling in Biosim, and (3) developed an understanding of the role machine learning in designing control systems for advanced life support.

Subramanian, Devika↗

NASA NTRS2005

Learning for autonomous navigation : extrapolating from underfoot to the far field

Autonomous off-road navigation of robotic ground vehicles has important applications on Earth and in space exploration. Progress in this domain has been retarded by the limited lookahead range of 3-D sensors and by the difficulty of preprogramming systems to understand the traversability of the wide variety of terrain they can encounter. Enabling robots to learn from experience may alleviate both of these problems. We define two paradigms for this, learning from 3-D geometry and learning from proprioception, and describe initial instantiations of them we have developed under DARPA and NASA programs. Field test results show promise for learning traversability of vegetated terrain, learning to extend the lookahead range of the vision system, and learning how slip varies with slope.

autonomous robots↗

NASA NTRS2006

Learning Grasp Context Distinctions that Generalize

Control-based approaches to grasp synthesis create grasping behavior by sequencing and combining control primitives. In the absence of any other structure, these approaches must evaluate a large number of feasible control sequences as a function of object shape, object pose, and task. This work explores a new approach to grasp synthesis that limits consideration to variations on a generalized localize-reach-grasp control policy. A new learning algorithm, known as schema structured learning, is used to learn which instantiations of the generalized policy are most likely to lead to a successful grasp in different problem contexts. Two experiments are described where Dexter, a bimanual upper torso, learns to select an appropriate grasp strategy as a function of object eccentricity and orientation. In addition, it is shown that grasp skills learned in this way can generalize to new objects. Results are presented showing that after learning how to grasp a small, representative set of objects, the robot's performance quantitatively improves for similar objects that it has not experienced before.

Platt, Robert↗

NASA NTRS2009

Evaluation of Learning Associated with Multiple Exposures to Computerized Dynamic Posturography

Computerized dynamic posturography has been used to quantitatively assess the time course of functional sensorimotor recovery after exposure to spaceflight or to groundbased analogs such as head-down bed rest. An assessment of balance recovery may be confounded as subjects develop new strategies through repeated exposures to test paradigms. The purpose of this control study was to characterize the learning effects of sensory organization and motor control tests across multiple sessions. METHODS: Twenty-eight healthy subjects were tested over four sessions. To examine the effects of between-session interval, subjects were assigned to one of four groups in which the interval between the 1 st and 2nd sessions was 7 (+/- 1) days, 14 (+/-1) days, 28 (+/-2) days, or 56 (+/-3) days. The interval between remaining sessions was 28 (+/-4) days. Peak-to-peak anterior-posterior sway was measured during standard Sensory Organization Tests (SOTs) using either fixed or unstable sway-referenced support with eyes open, eyes closed, or sway-referenced vision. Sway was also measured during modified SOTs using eyes-closed conditions with either static or dynamic head tilts. Postural recovery to unexpected support surface perturbations (translations or rotations) was measured during Motor Control Tests. The test order was block randomized across subjects. RESULTS: The learning effects varied with test condition. There were no measurable differences with a stable support surface. The more challenging conditions (unstable support surface with and without head tilts) led to greater differences and took more trials to stabilize. The effect of time interval between the first two sessions was negligible across conditions. Evidence suggested that learning carried across similar conditions (such as unstable support SOTs). DISCUSSION: Familiarization session and/or trials are recommended to minimize learning effects when characterizing functional recovery after exposure to altered sensory environments. The number of practice trials required depends on task difficulty and similarity across conditions. Learning statement: This presentation will review the learning effects of computerized d

Dean, S. Lance↗

NASA NTRS2009

Active Learning with Irrelevant Examples

An improved active learning method has been devised for training data classifiers. One example of a data classifier is the algorithm used by the United States Postal Service since the 1960s to recognize scans of handwritten digits for processing zip codes. Active learning algorithms enable rapid training with minimal investment of time on the part of human experts to provide training examples consisting of correctly classified (labeled) input data. They function by identifying which examples would be most profitable for a human expert to label. The goal is to maximize classifier accuracy while minimizing the number of examples the expert must label. Although there are several well-established methods for active learning, they may not operate well when irrelevant examples are present in the data set. That is, they may select an item for labeling that the expert simply cannot assign to any of the valid classes. In the context of classifying handwritten digits, the irrelevant items may include stray marks, smudges, and mis-scans. Querying the expert about these items results in wasted time or erroneous labels, if the expert is forced to assign the item to one of the valid classes. In contrast, the new algorithm provides a specific mechanism for avoiding querying the irrelevant items. This algorithm has two components: an active learner (which could be a conventional active learning algorithm) and a relevance classifier. The combination of these components yields a method, denoted Relevance Bias, that enables the active learner to avoid querying irrelevant data so as to increase its learning rate and efficiency when irrelevant items are present. The algorithm collects irrelevant data in a set of rejected examples, then trains the relevance classifier to distinguish between labeled (relevant) training examples and the rejected ones. The active learner combines its ranking of the items with the probability that they are relevant to yield a final decision about which item to present to the expert for labeling. Experiments on several data sets have demonstrated that the Relevance Bias approach significantly decreases the number of irrelevant items queried and also accelerates learning speed.

Wagstaff, Kiri↗