Search NASA⌕ Search

SEARCH · Search NASA

Results for “Policy optimization”

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.

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

At least 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Optimizing Patient-Specific Medication Regimen Policies Using Wearable Sensors in Parkinson’s Disease

Effective treatment of Parkinson’s disease (PD) is a continual challenge for healthcare providers, and providers can benefit from leveraging emerging technologies to supplement traditional clinic care. We develop a data-driven reinforcement learning (RL) framework to optimize PD medication regimens through wearable sensors. We leverage a data set of n = 26 PD patients who wore wrist-mounted movement trackers for two separate six-day periods. Using these data, we first build and validate a simulation model of how individual patients’ movement symptoms respond to medication administration. We then pair this simulation model with an on-policy RL algorithm that recommends optimal medication types, timing, and dosages during the day while incorporating human-in-the-loop considerations on medication administration. The results show that the RL-prescribed medication regimens outperform physicians’ medication regimens, despite physicians having access to the same data as the RL agent. To validate our results, we assess our wearable-based RL medication regimens using n = 399 PD patients from the Parkinson’s Progression Markers Initiative data set. We show that the wearable-based RL medication regimens would lead to significant symptom improvement for these patients, even more so than training RL policies directly from this data set. In doing so, we show that RL models from even small data sets of wearable data can offer novel, generalizable clinical insights and medication strategies, which may outperform those derived from larger data sets without wearable data.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Physics-informed Deep Reinforcement Learning-based Control in Power systems

Incorporating physics information into the deep reinforcement learning (DRL) process is a promising approach for addressing the challenges faced in learning-based control design problems for physical systems. Power grid dynamics, being a physical system, adheres to specific physical laws, constraints, as well as operational and control rules. Therefore, consideration of such physics-based law improves the learning process drastically. In general, traditional grid control schemes rely on rule-based mechanisms that cannot adapt to changing operating conditions. To improve the adaptability and computation time, recent research has seen a surge of DRL-based applications in power grid control. A generic DRL-based control design imposes the system performance requirements through the design of reward functions. In some cases, some of the important physics information is injected through this reward function. However, due to the complex dynamics and large state-action space, learning an optimal DRL policy often becomes challenging. Inspired by the latest developments in general machine learning (ML) research, power system researchers have been investigating more direct ways of incorporating physics knowledge into DRL training. This chapter specifically focuses on these aspects of physics-informed DRL designs in grid control. It discusses the significance, applications, research gaps, and open problems that need to be addressed in future research.

artificial intelligence, machine learning↗
DOE OSTI2016

Conditions for the Solvability of the Linear Programming Formulation for Constrained Discounted Markov Decision Processes

We consider a discrete-time constrained discounted Markov decision process (MDP) with Borel state and action spaces, compact action sets, and lower semi-continuous cost functions. We introduce a set of hypotheses related to a positive weight function which allow us to consider cost functions that might not be bounded below by a constant, and which imply the solvability of the linear programming formulation of the constrained MDP. In particular, we establish the existence of a constrained optimal stationary policy. Our results are illustrated with an application to a fishery management problem.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Evaluating Gaussian process metamodels and sequential designs for noisy level set estimation

Abstract We consider the problem of learning the level set for which a noisy black-box function exceeds a given threshold. To efficiently reconstruct the level set, we investigate Gaussian process (GP) metamodels. Our focus is on strongly stochastic simulators, in particular with heavy-tailed simulation noise and low signal-to-noise ratio. To guard against noise misspecification, we assess the performance of three variants: (i) GPs with Student- t observations; (ii) Student- t processes (TPs); and (iii) classification GPs modeling the sign of the response. In conjunction with these metamodels, we analyze several acquisition functions for guiding the sequential experimental designs, extending existing stepwise uncertainty reduction criteria to the stochastic contour-finding context. This also motivates our development of (approximate) updating formulas to efficiently compute such acquisition functions. Our schemes are benchmarked by using a variety of synthetic experiments in 1–6 dimensions. We also consider an application of level set estimation for determining the optimal exercise policy of Bermudan options in finance.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Revisiting the ODE Method for Recursive Algorithms: Fast Convergence Using Quasi Stochastic Approximation

Several decades ago, Profs. Sean Meyn and Lei Guo were postdoctoral fellows at ANU, where they shared interest in recursive algorithms. It seems fitting to celebrate Lei Guo's 60th birthday with a review of the ODE Method and its recent evolution. The method has been regarded as a technique for algorithm analysis. It is argued that this viewpoint is backwards: The original stochastic approximation method was surely motivated by an ODE, and tools for analysis came much later (based on establishing robustness of Euler approximations). The paper presents a brief survey of recent research in machine learning that shows the power of algorithm design in continuous time, following by careful approximation to obtain a practical recursive algorithm. While these methods are usually presented in a stochastic setting, this is not a prerequisite. In fact, recent theory shows that rates of convergence can be dramatically accelerated by applying techniques inspired by quasi Monte-Carlo. Subject to conditions, the optimal rate of convergence can be obtained by applying the averaging technique of Polyak and Ruppert. The conditions are not universal, but theory suggests alternatives to achieve acceleration. The theory is illustrated with applications to gradient-free optimization, and policy gradient algorithms for reinforcement learning.

learning and adaptive systems in artificial intell↗
DOE OSTI2023

Online transfer learning strategy for enhancing the scalability and deployment of deep reinforcement learning control in smart buildings

In recent years, advanced control strategies based on Deep Reinforcement Learning (DRL) proved to be effective in optimizing the management of integrated energy systems in buildings, reducing energy costs and improving indoor comfort conditions when compared to traditional reactive controllers. However, the scalability and implementation of DRL controllers are still limited since they require a considerable amount of time before converging to a near-optimal solution. This issue is currently addressed in literature through the offline pre-training of the DRL agent. However this solution results in two main critical issues: (1) the need to develop a building surrogate model to perform the training task, and (2) the need to perform a fine-tuning process over several training episodes to obtain a near-optimal control policy. In this context, this paper introduces an Online Transfer Learning (OTL) strategy that exploits two knowledge-sharing techniques, weight-initialization and imitation learning, to transfer a DRL control policy from a source office building to various target buildings in a simulation environment coupling EnergyPlus and Python. A DRL controller based on discrete Soft Actor–Critic (SAC) is trained on the source building to manage the operation of a cooling system consisting of a chiller and a thermal storage. Several target buildings are defined to benchmark the performance of the OTL strategy with that of a Rule-Based Controller (RBC) and two DRL-based control strategies, deployed in offline and online fashion. The strategy adopted for OTL emulates the real world implementation with a simulation process by implementing the transferred DRL agent for a single episode in the target buildings. Target buildings have the same geometrical features and are served by the same energy system as the source building, but differ in terms of weather conditions, electricity price schedules, occupancy patterns, and building envelope efficiency levels. The results show that the OTL strategy can reduce the cumulated sum of temperature violations on average by 50% and 80% respectively when compared to RBC and online DRL while enhancing the energy system operation with electricity cost savings ranging between 20% and 40%. Furthermore, the OTL agent performs slightly worse than the offline DRL controller but it does not require any modeling effort and can be implemented directly on target buildings emulating a real-world implementation.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2025

Nuclear microreactor transient and load-following control with deep reinforcement learning

The economic feasibility of nuclear microreactors will depend on minimizing operating costs through advancements in autonomous control, especially when these microreactors are operating alongside other types of energy systems (e.g., renewable energy). This study explores the application of deep reinforcement learning (RL) for real-time drum control in microreactors, exploring performance in regard to load-following scenarios. By leveraging a point kinetics model with thermal and xenon feedback, we first establish a baseline using a single-output RL agent, then compare it against a traditional proportional–integral–derivative (PID) controller. This study demonstrates that RL controllers, including both single- and multi-agent RL (MARL) frameworks, can achieve similar or even superior load-following performance as traditional PID control across a range of load-following scenarios. In short transients, the RL agent was able to reduce the tracking error rate in comparison to PID by one half to one third. Over extended 300-minute load-following scenarios in which xenon feedback becomes a dominant factor, PID maintained better accuracy, but RL still remained within a 1% error margin despite being trained only on short-duration scenarios. This highlights RL’s strong ability to generalize and extrapolate to longer, more complex transients, affording substantial reductions in training costs and reduced overfitting. Furthermore, when control was extended to multiple drums, MARL enabled independent drum control as well as maintained reactor symmetry constraints without sacrificing performance---an objective that standard single-agent RL could not learn. We also found that, as increasing levels of Gaussian noise were added to the power measurements, the RL controllers were able to maintain lower error rates than PID, and to do so with at least 10% and upwards of 150% less control effort. These findings illustrate RL's potential for autonomous nuclear reactor control, laying the groundwork for future integration into high-fidelity simulations and experimental validation efforts.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2020

Data-based and secure switched cyber–physical systems

In this work, we develop a completely model-free moving target defense framework for the detection and mitigation of sensor and/or actuator attacks in cyber–physical systems with dynamics that evolve in discrete-time. We incorporate an intrusion detection mechanism based on an approximate dynamic programming technique that learns the policies for optimal regulation and optimal tracking while simultaneously defending against actuator and sensor attacks in a model-free fashion. Switching rules are leveraged to force proactive and reactive defense mechanisms as well as, guarantee the stability of the equilibrium point. Finally, as a case study, we apply the proposed moving target defense framework to a DC–DC converter that is used in electric vehicles.

42 ENGINEERING↗
DOE OSTI2021

Barrier Function-based Reinforcement Learning for Emergency Control of Power Systems

Under voltage load shedding has been considered as a standard and effective measure to recover the voltage stability of the electric power grid under emergency and severe conditions. However, this scheme usually trips a massive amount of load which can be unnecessary and harmful to customers. Recently, deep reinforcement learning (RL) has been regarded and adopted as a promising approach that can significantly reduce the amount of load shedding. However, like most existing machine learning (ML)-based control techniques, RL control usually cannot guarantee the safety of the systems under control. In this paper, we introduce a novel safe RL method for load shedding of power systems, that can enhance the safe voltage recovery of the electric power grid after experiencing faults. Unlike standard RL method, the safe RL method integrates a Barrier function into the reward function. Consequently, the optimal control policy can render the power system to avoid the safety bounds. This method is general and can be applied to other safety-critical control problems. Numerical simulations on the 39-bus IEEE benchmark is performed to demonstrate the effectiveness of the proposed safe RL emergency control, as well as its adaptive capability to faults not seen in the training.

Vu, Thanh Long↗
DOE OSTI2024

A Transfer Learning Strategy for Improving the Data Efficiency of Deep Reinforcement Learning Control in Smart Buildings

Reinforcement learning (RL) is a powerful tool that has shown promising results in many domains such as robotics and game-playing. Because RL algorithms learn optimal control policies by continuously interacting with their environments, these algorithms require a lot of data to learn, which limits their application to a wide range of domains. For this reason, there is an immense need for improving the training and data efficiency of RL. Towards addressing this research gap, this paper proposes a transfer learning (TL) approach to improve the efficiency of the RL algorithms by reducing data need and, thus, reducing training time. To demonstrate the proposed approach, a knowledge transfer from a set of buildings to another building was conducted. The results show that the proposed TL approach is a promising method that can efficiently harness the information from similar RL tasks and reduce the data needs of RL algorithms.

Amasyali, Kadir↗
DOE OSTI2019

Data and Thread Placement in NUMA Architectures: A Statistical Learning Approach

Nowadays, NUMA architectures are common in compute-intensive systems. Achieving high performance for multi-threaded application requires both a careful placement of threads on computing units and a thorough allocation of data in memory. Finding such a placement is a hard problem to solve, because performance depends on complex interactions in several layers of the memory hierarchy. In this paper we propose a black-box approach to decide if an application execution time can be impacted by the placement of its threads and data, and in such a case, to choose the best placement strategy to adopt. We show that it is possible to reach near-optimal placement policy selection. Furthermore, solutions work across several recent processor architectures and decisions can be taken with a single run of low overhead profiling.

data↗
DOE OSTI2024

Reinforcement learning applied to dilute combustion control for increased fuel efficiency

To reduce the modeling burden for control of spark-ignition engines, reinforcement learning (RL) has been applied to solve the dilute combustion limit problem. Q-learning was used to identify an optimal control policy to adjust the fuel injection quantity in each combustion cycle. A physics-based model was used to determine the relevant states of the system used for training the control policy in a data-efficient manner. The cost function was chosen such that high cycle-to-cycle variability (CCV) at the dilute limit was minimized while maintaining stoichiometric combustion as much as possible. Experimental results demonstrated a reduction of CCV after the training period with slightly lean combustion, contributing to a net increase in fuel conversion efficiency of 1.33%. To ensure stoichiometric combustion for three-way catalyst compatibility, a second feedback loop based on an exhaust oxygen sensor was incorporated into the fuel quantity controller using a slow proportional-integral (PI) controller. The closed-loop experiments showed that both feedback loops can cooperate effectively, maintaining stoichiometric combustion while reducing combustion CCV and increasing fuel conversion efficiency by 1.09%. Finally, a modified cost function was proposed to ensure stoichiometric combustion with a single controller. In addition, the learning period was shortened by half to evaluate the RL algorithm performance on limited training time. Experimental results showed that the modified cost function could achieve the desired CCV targets, however, the learning time was reduced by half and the fuel conversion efficiency increased only by 0.30%.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2024

Decision-making based on Markov decision process in integrated artificial reasoning framework—Part I: Theory

This paper presents a decision-making framework based on an integrated artificial reasoning framework and Markov decision process (MDP). The integrated artificial reasoning framework provides a physics-based approach that converts system information into state transition models, and the analysis result will be represented by the transition probabilities that can be used with an MDP to find a traceable and explainable optimal pathway. A dynamic Bayesian network (DBN) is well suited for representing the structure of an MDP. The causality information among process variables (or among subsystems) is mathematically represented in a DBN by the conditional probabilities of the node’s states provided different probabilities of the parent node’s states. To define node states in a physically understandable manner, we used multilevel flow modeling (MFM). An MFM follows the fundamental energy and mass conservation laws and supports the selection of process variables that represent the system of interest so that causal relations among process variables are properly captured. An MFM-based DBN supports developing state transition models in an MDP to capture the effect of process variables of system having physical relations. The operators of the target system can capture stochastic system dynamics as multiple subsystem state transitions based on their physical relations and uncertainties coming from component degradation or random failures. We analyzed a simplified exemplary system to illustrate an optimal operational policy using the suggested approach.

Markov decision process↗
DOE OSTI2022

Sequential Decision Making (SDM) for Mesh Refinement and Model Selection in Multiscale, Multi-Physics Applications

Intelligent automation and decision support are needed to enhance computational efficiency and robustness in multiscale and multi-physics problems, including materials science, manufacturing, and climate and weather modeling. Current scientific computing approaches for enabling decisions by scientists fail to explore the role of learning, reasoning, and probabilistic planning. Often these decisions are not performed in real-time during the computation but are made prior to the start of the computation, which must be interrupted in order to make changes to the prior choices. Such interruptions at different stages of the computation increase the total computing time and the need for a human expert to frequently monitor the results. State of art scientific computing methods consist of rule-based algorithms that cannot automatically adapt to a dynamically changing computing environment. The development of a Sequential Decision Making (SDM) framework will automate scientific computing by optimizing the policies for mesh refinement, time-stepping, model and algorithm selection, resource allocation, and pre and post-processing. Our agent SDM framework for scientific computing will consist of data-driven learning (Classifier), automated reasoning (contextual knowledge), and probabilistic planning (Reinforcement Learning). In this project, we focused on three problems to demonstrate our SDM framework on a set of ordinary and partial differential equations. Classification of Lorenz system regions using Feed-Forward Neural Networks examined learning in the SDM framework. On the other hand, reasoning and planning in the SDM framework were used in two problems: adaptive time-stepping for nonlinear ODEs using on-policy RL algorithms, and adaptive mesh refinement for 2-D PDEs using off-policy RL algorithms.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

SCORE (Synthesis of COnsists as Rolling Energy microgrids) (Final Technical Report)

The SCORE toolset is an open source, web-based application to assess the impact of new powering technologies on railroad performance, specifically technologies capable of both putting power into the rail (motive force) and taking power from the rail (regeneration). SCORE’s primary goal is generate trade studies to analyze different powering and train make-up options to minimize energy usage and greenhouse gas generation. At the core of generating these trade spaces is calculating the optimal powering policy for the train given the makeup of the train, the route, and time constraints. This paper presents details on the algorithms used in SCORE to compute this powering policies that is fast and accurate, discusses its implementation in an Energy-Longitudinal Train Dynamics (E-LTD) model, compares it to naïve approaches, and demonstrates its use across a variety of train/route pairs.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS1982

A Markov chain model for reliability growth and decay

A mathematical model is developed to describe a complex system undergoing a sequence of trials in which there is interaction between the internal states of the system and the outcomes of the trials. For example, the model might describe a system undergoing testing that is redesigned after each failure. The basic assumptions for the model are that the state of the system after a trial depends probabilistically only on the state before the trial and on the outcome of the trial and that the outcome of a trial depends probabilistically only on the state of the system before the trial. It is shown that under these basic assumptions, the successive states form a Markov chain and the successive states and outcomes jointly form a Markov chain. General results are obtained for the transition probabilities, steady-state distributions, etc. A special case studied in detail describes a system that has two possible state ('repaired' and 'unrepaired') undergoing trials that have three possible outcomes ('inherent failure', 'assignable-cause' 'failure' and 'success'). For this model, the reliability function is computed explicitly and an optimal repair policy is obtained.

Siegrist, K.↗