Results for “practical reinforcement learning” — Page 2

DOE OSTI2026

Discovering the Most Severe K-Point Failure Based on Reinforcement Learning: Preprint

Smart devices are essential to ensure the stability of the power grid and resilience to intermittent energy production. However, smart devices can also be the target of cyber adversaries that may exploit false data injection attacks (FDIAs) to induce unstable grid conditions. A practical consideration of FDIA mitigation approaches is addressed here: given a finite available budget, for which smart device should cyber-threat mitigation be deployed first? In this work, this question is answered by identifying the so-called most-sensitive devices, i.e., the devices that, if compromised, can let an adversary induce the most serious grid instabilities. The method proposed utilizes an adversarial reinforcement learning (RL) framework to identify the k-mostsensitive smart devices (here, smart inverters). The adversarial agent can tamper with the compromised inverters' active and reactive operating power setup points, with the goal of maximizing voltage deviations. Numerical results show that the proposed RL method finds the optimal attack scenarios for 1-point failure and the near-optimal solution for the 2-point case. Additionally, the proposed RL method achieves an 8.8 speed-up ratio in running time compared to the brute force method for the 2-point case.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

A Novel Deep Reinforcement Learning Approach to Traffic Signal Control with Connected Vehicles

The advent of connected vehicle (CV) technology offers new possibilities for a revolution in future transportation systems. With the availability of real-time traffic data from CVs, it is possible to more effectively optimize traffic signals to reduce congestion, increase fuel efficiency, and enhance road safety. The success of CV-based signal control depends on an accurate and computationally efficient model that accounts for the stochastic and nonlinear nature of the traffic flow. Without the necessity of prior knowledge of the traffic system’s model architecture, reinforcement learning (RL) is a promising tool to acquire the control policy through observing the transition of the traffic states. In this paper, we propose a novel data-driven traffic signal control method that leverages the latest in deep learning and reinforcement learning techniques. By incorporating a compressed representation of the traffic states, the proposed method overcomes the limitations of the existing methods in defining the action space to include more practical and flexible signal phases. The simulation results demonstrate the convergence and robust performance of the proposed method against several existing benchmark methods in terms of average vehicle speeds, queue length, wait time, and traffic density.

42 ENGINEERING↗

NASA NTRS1992

Fuzzy logic and neural network technologies

Applications of fuzzy logic technologies in NASA projects are reviewed to examine their advantages in the development of neural networks for aerospace and commercial expert systems and control. Examples of fuzzy-logic applications include a 6-DOF spacecraft controller, collision-avoidance systems, and reinforcement-learning techniques. The commercial applications examined include a fuzzy autofocusing system, an air conditioning system, and an automobile transmission application. The practical use of fuzzy logic is set in the theoretical context of artificial neural systems (ANSs) to give the background for an overview of ANS research programs at NASA. The research and application programs include the Network Execution and Training Simulator and faster training algorithms such as the Difference Optimized Training Scheme. The networks are well suited for pattern-recognition applications such as predicting sunspots, controlling posture maintenance, and conducting adaptive diagnoses.

Villarreal, James A.↗

DOE OSTI2020

Do optimization methods in deep learning applications matter?

With advances in deep learning, exponential data growth and increasing model complexity, developing efficient optimization methods are attracting much research attention. Several implementations favor the use of Conjugate Gradient (CG) and Stochastic Gradient Descent (SGD) as being practical and elegant solutions to achieve quick convergence, however, these optimization processes also present many limitations in learning across deep learning applications. Recent research is exploring higher-order optimization functions as better approaches, but these present very complex computational challenges for practical use. Comparing first and higher-order optimization functions, in this paper, our experiments reveal that Levemberg-Marquardt (LM) significantly supersedes optimal convergence but suffers from very large processing time increasing the training complexity of both, classification and reinforcement learning problems. Our experiments compare off-the-shelf optimization functions(CG, SGD, LM and L-BFGS) in standard CIFAR, MNIST, CartPole and FlappyBird experiments.The paper presents arguments on which optimization functions to use and further, which functions would benefit from parallelization efforts to improve pretraining time and learning rate convergence.

Ozyildirim, Buse Melis↗

DOE OSTI2024

Deep Reinforcement Learning for Microgrid Cost Optimization Considering Load Flexibility

This paper proposes a novel Soft-Actor-Critic (SAC) based Deep Reinforcement Learning (DRL) method for optimizing the cost of microgrid operation by leveraging load flexibility. The proposed SAC-DRL method is designed to coordinate the control of distributed energy resources (DERs) and flexible load, addressing practical energy billing formation by power distribution utilities. Key contributions include an innovative reward function to mitigate sparse reward challenges and a mixed control strategy for discrete and continuous variables, ensuring radial network topology and minimizing power loss. We evaluate the proposed method on the model of a real microgrid located in Southern California, U.S.. The SAC-DRL model is tested to demonstrate its efficacy in reducing grid dependence, optimizing resource use, and minimizing costs. The results highlight the potential of DRL in modern energy systems, offering a sustainable and economically efficient solution for energy management in microgrids.

deep reinforcement learning↗

NASA NTRS1998

Preliminary Work for Examining the Scalability of Reinforcement Learning

Researchers began studying automated agents that learn to perform multiple-step tasks early in the history of artificial intelligence (Samuel, 1963; Samuel, 1967; Waterman, 1970; Fikes, Hart & Nilsonn, 1972). Multiple-step tasks are tasks that can only be solved via a sequence of decisions, such as control problems, robotics problems, classic problem-solving, and game-playing. The objective of agents attempting to learn such tasks is to use the resources they have available in order to become more proficient at the tasks. In particular, each agent attempts to develop a good policy, a mapping from states to actions, that allows it to select actions that optimize a measure of its performance on the task; for example, reducing the number of steps necessary to complete the task successfully. Our study focuses on reinforcement learning, a set of learning techniques where the learner performs trial-and-error experiments in the task and adapts its policy based on the outcome of those experiments. Much of the work in reinforcement learning has focused on a particular, simple representation, where every problem state is represented explicitly in a table, and associated with each state are the actions that can be chosen in that state. A major advantage of this table lookup representation is that one can prove that certain reinforcement learning techniques will develop an optimal policy for the current task. The drawback is that the representation limits the application of reinforcement learning to multiple-step tasks with relatively small state-spaces. There has been a little theoretical work that proves that convergence to optimal solutions can be obtained when using generalization structures, but the structures are quite simple. The theory says little about complex structures, such as multi-layer, feedforward artificial neural networks (Rumelhart & McClelland, 1986), but empirical results indicate that the use of reinforcement learning with such structures is promising. These empirical results make no theoretical claims, nor compare the policies produced to optimal policies. A goal of our work is to be able to make the comparison between an optimal policy and one stored in an artificial neural network. A difficulty of performing such a study is finding a multiple-step task that is small enough that one can find an optimal policy using table lookup, yet large enough that, for practical purposes, an artificial neural network is really required. We have identified a limited form of the game OTHELLO as satisfying these requirements. The work we report here is in the very preliminary stages of research, but this paper provides background for the problem being studied and a description of our initial approach to examining the problem. In the remainder of this paper, we first describe reinforcement learning in more detail. Next, we present the game OTHELLO. Finally we argue that a restricted form of the game meets the requirements of our study, and describe our preliminary approach to finding an optimal solution to the problem.

Clouse, Jeff↗

NASA NTRSDate not supplied

Structural Carbon Nanotube Development

Mechanical properties of carbon nanotubes (CNTs) at the nanoscale suggest their potential to enable significantly lighter structures of interest in aerospace applications. As different formats of the material became available over the last 20 years, understanding of how CNTs contribute to improvements in mechanical properties of structural composites has evolved.Although the material is now available in large quantities that permit the development of composite fabrication processes, the retention of properties that make these materials attractive on the nano scale remains a challenge in large assemblies of CNTs. The work to be presented will summarize lessons learned in our efforts to produce carbon nanotube composites with tensile properties that begin to rival those of carbon fiber reinforced polymer composites. Challenges that need to be overcome for practical adoption of this emerging material system will be considered.

Carbon nanotube↗

DOE OSTI2021

Deep Reinforcement Learning Enabled Physical-Model-Free Two-Timescale Voltage Control Method for Active Distribution Systems

Active distribution networks are being challenged by frequent and rapid voltage violations due to renewable energy integration. Conventional model-based voltage control methods rely on accurate parameters of the distribution networks, which are difficult to achieve in practice. This paper proposes a novel physical-model-free two-timescale voltage control framework for active distribution systems. To achieve fast control of PV inverters, the whole network is first partitioned into several subnetworks using voltage-reactive power sensitivity. Then, the scheduling of PV inverters in the multiple sub-networks is formulated as Markov games and solved by a multi-agent soft actor-critic (MASAC) algorithm, where each subnetwork is modeled as an intelligent agent. All agents are trained in a centralized manner to learn a coordinated strategy while being executed based on only local information for fast response. For the slower time-scale control, OLTCs and switched capacitors are coordinated by a single agent-based SAC algorithm using the global information with considering control behaviors of the inverters. Particularly, the two-level agents are trained concurrently with information exchange according to the reward signal calculated from the data-driven surrogate model. Comparative tests with different benchmark methods on IEEE 33-and 123-bus systems and 342-node low voltage distribution system demonstrate that the proposed method can effectively mitigate the fast voltage violations and achieve systematical coordination of different voltage regulation assets without the knowledge of accurate system model.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2022

On-policy learning-based deep reinforcement learning assessment for building control efficiency and stability

Artificial intelligence technologies have emerged as a game changer not only in specific applications such as image recognition and machine translation but also in many scientific domains. In particular, as deep reinforcement learning (DRL) has shown great success in complex control problems, DRL-based control has been considered as a potential solution to efficiently control and manage building systems. However, broad assessment of DRL-based building control is still required to characterize their pros and cons in comparison with conventional building control methods (e.g., rule-based feedback controls). In this paper, we assessed DRL-based controls with on-policy learning-based algorithms and continuous control actions for cooling control of large office buildings in the summer season to minimize whole-building energy use and occupant discomfort. We compared DRL-based control methods with two baseline control methods: (1) a pre-determined schedule with supply temperature and static pressure setpoints, and (2) advanced reset method that adjusts setpoints based on heuristic rules, i.e., ASHRAE Guideline 36. We also tested the DRL algorithms to evaluate their performances in multiple climate locations. We found that DRL-based control methods outperformed the baseline control methods in terms of energy savings while maintaining a thermal comfort. DRL reduced energy use between ~4%–22% on average compared to the baseline methods, depending on climate location. We also evaluated DRL-based control in terms of control stability and showed that DRL-based methods should address the span of hardware lifetimes in practical operations.

control stability↗

DOE OSTI2024

Practical and Optimal Sequential Bayesian Experimental Design for Complex Systems Incorporating Human Experimenter Preferences (Final Scientific/Technical Report)

Experiments are indispensable for developing models of complex systems. Carefully designed experiments can provide substantial savings for these expensive data-acquisition opportunities. However, designs based on heuristics are often suboptimal for systems with multiphysics, nonlinear dynamics, and uncertain and noisy environments. Optimal experimental design, while leveraging predictive models, seeks to systematically quantify and maximize the value of experiments. In this project, we focused on the design of multiple experiments, where current approaches are largely suboptimal: batch-design does not adapt to new data acquired during the experiment campaign (no feedback), and greedy/myopic design ignores future dynamics and consequences (no lookahead). We developed the mathematical framework and computational methods for sequential optimal experimental design (sOED) for complex systems. We enabled tractable model-based sOED in a rigorous manner through novel algorithms based on reinforcement learning, and investigated the effects of human experimenters on the design process. Our methods are fully Bayesian, able to quantify and update uncertainty in a principled manner. The traits aimed by our approach—mathematical rigor and optimality, human effects and uncertainty quantification, computational practicality—are crucial for elevating the standards of artificial intelligence (AI) to support decision-making in scientific domains, and contribute toward trust and realistic adoption of AI in experimental design practice.

97 MATHEMATICS AND COMPUTING↗

NASA NTRSDate not supplied

Discovery and Analysis of Rare High-Impact Failure Modes using Adversarial RL-Informed Sampling

Adaptive learning agents have tremendous potential to handle critical tasks currently performed by humans. Unfortunately, due to their complexity, it can be difficult to verify that these learning agents do not have critical failure modes. Standard verification and validation methods often do not apply directly to learning agents and Monte Carlo methods have difficulty covering even a small fraction of the state space, especially in multiagent systems or over long time horizons. To overcome this difficulty, we demonstrate an adaptive stress-testing method based on reinforcement learning of correlations that raise the probability of failure. This approach has three key properties: (1) it is able to find rare failure modes with far greater sample efficiency than Monte Carlo methods, (2) it can estimate the true probability of a failure mode despite the inherent bias in the learning method, and (3) it is capable of learning and resampling compact representations of multimodal failure spaces. These properties are important in practice as we need to find disparate failure modes while accounting for their actual relevance. This is a significant advantage over traditional adaptive stress testing methods that give abstract likelihoods of particular failure instances, but cannot estimate the probability of a broader failure mode. We test our algorithm on a simple problem from the aviation domain where an autonomous aircraft lands in gusty wind conditions. The results suggest that we can find failure modes with far fewer samples than the Monte Carlo approach and simultaneously estimate the probability of failure.

reinforcement learning↗

NASA NTRSDate not supplied

Discovery and Analysis of Rare High-Impact Failure Modes using Adversarial RL-Informed Sampling

Adaptive learning agents have tremendous potential to handle critical tasks currently performed by humans. Unfortunately, due to their complexity, it can be difficult to verify that these learning agents do not have critical failure modes. Standard verification and validation methods often do not apply directly to learning agents and Monte Carlo methods have difficulty covering even a small fraction of the state space, especially in multiagent systems or over long time horizons. To overcome this difficulty, we demonstrate an adaptive stress-testing method based on reinforcement learning of correlations that raise the probability of failure. This approach has three key properties: (1) it is able to find rare failure modes with far greater sample efficiency than Monte Carlo methods, (2) it can estimate the true probability of a failure mode despite the inherent bias in the learning method, and (3) it is capable of learning and resampling compact representations of multimodal failure spaces. These properties are important in practice as we need to find disparate failure modes while accounting for their actual relevance. This is a significant advantage over traditional adaptive stress testing methods that give abstract likelihoods of particular failure instances, but cannot estimate the probability of a broader failure mode. We test our algorithm on a simple problem from the aviation domain where an autonomous aircraft lands in gusty wind conditions. The results suggest that we can find failure modes with far fewer samples than the Monte Carlo approach and simultaneously estimate the probability of failure.

Validation↗

NASA NTRSDate not supplied

Discovery and Analysis of Rare High-Impact Failure Modes using Adversarial RL-Informed Sampling

Adaptive learning agents have tremendous potential to handle critical tasks currently performed by humans. Unfortunately, due to their complexity, it can be difficult to verify that these learning agents do not have critical failure modes. Standard verification and validation methods often do not apply directly to learning agents and Monte Carlo methods have difficulty covering even a small fraction of the state space, especially in multiagent systems or over long time horizons. To overcome this difficulty, we demonstrate an adaptive stress-testing method based on reinforcement learning of correlations that raise the probability of failure. This approach has three key properties: (1) it is able to find rare failure modes with far greater sample efficiency than Monte Carlo methods, (2) it can estimate the true probability of a failure mode despite the inherent bias in the learning method, and (3) it is capable of learning and resampling compact representations of multimodal failure spaces. These properties are important in practice as we need to find disparate failure modes while accounting for their actual relevance. This is a significant advantage over traditional adaptive stress testing methods that give abstract likelihoods of particular failure instances, but cannot estimate the probability of a broader failure mode. We test our algorithm on a simple problem from the aviation domain where an autonomous aircraft lands in gusty wind conditions. The results suggest that we can find failure modes with far fewer samples than the Monte Carlo approach and simultaneously estimate the probability of failure.

Validation↗

DOE OSTI2023

Efficient Reinforcement Learning for Real-Time Hardware-Based Energy System Experiments: Preprint

In the context of urgent climate challenges and the pressing need for rapid technology development, Reinforcement Learning (RL) stands as a compelling data-driven method for controlling real-world physical systems. However, RL implementation often entails time-consuming and computationally intensive data collection and training processes, rendering them inefficient for real-time applications that lack non-real-time models. To address these limitations, real-time emulation techniques have emerged as valuable tools for the lab-scale rapid prototyping of intricate energy systems. While emulated systems offer a bridge between simulation and reality, they too face constraints, hindering comprehensive characterization, testing, and development. In this research, we construct a surrogate model using limited data from simulated systems, enabling an efficient and effective training process for a Double Deep Q-Network (DDQN) agent for future deployment. Our approach is illustrated through a hydropower application, demonstrating the practical impact of our approach on climate-related technology development.

deep Q-learning↗

DOE OSTI2024

Learning Robust Marking Policies for Adaptive Mesh Refinement

Here in this work, we revisit the marking decisions made in the standard adaptive finite element method (AFEM). Experience shows that a naïve marking policy leads to inefficient use of computational resources for adaptive mesh refinement (AMR). Consequently, using AMR in practice often involves ad-hoc or time-consuming offline parameter tuning to set appropriate parameters for the marking subroutine. To address these practical concerns, we recast AMR as a Markov decision process in which refinement parameters can be selected on-the-fly at run time, without the need for pre-tuning by expert users. In this new paradigm, the refinement parameters are also chosen adaptively via a marking policy that can be optimized using methods from reinforcement learning. We use the Poisson equation to demonstrate our techniques on h- and hp-refinement benchmark problems, and our experiments suggest that superior marking policies remain undiscovered for many classical AFEM applications. Furthermore, an unexpected observation from this work is that marking policies trained on one family of PDEs are sometimes robust enough to perform well on problems far outside the training family. For illustration, we show that a simple hp-refinement policy trained on 2D domains with only a single re-entrant corner can be deployed on far more complicated 2D domains, and even 3D domains, without significant performance loss. For reproduction and broader adoption, we accompany this work with an open-source implementation of our methods.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Ten questions concerning reinforcement learning for building energy management

As buildings account for approximately 40% of global energy consumption and associated greenhouse gas emissions, their role in decarbonizing the power grid is crucial. The increased integration of variable energy sources, such as renewables, introduces uncertainties and unprecedented flexibilities, necessitating buildings to adapt their energy demand to enhance grid resiliency. Consequently, buildings must transition from passive energy consumers to active grid assets, providing demand flexibility and energy elasticity while maintaining occupant comfort and health. This fundamental shift demands advanced optimal control methods to manage escalating energy demand and avert power outages. Reinforcement learning (RL) emerges as a promising method to address these challenges. Here, in this paper, we explore ten questions related to the application of RL in buildings, specifically targeting flexible energy management. We consider the growing availability of data, advancements in machine learning algorithms, open-source tools, and the practical deployment aspects associated with software and hardware requirements. Our objective is to deliver a comprehensive introduction to RL, present an overview of existing research and accomplishments, underscore the challenges and opportunities, and propose potential future research directions to expedite the adoption of RL for building energy management.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2022

Deep Reinforcement Learning From Demonstrations to Assist Service Restoration in Islanded Microgrids

Microgrids can be operated in island mode during utility grid outages to support service restoration and improve system resilience. To schedule and dispatch distributed energy resources (DERs) in an islanded microgrid, conventional model-based methods rely on accurate distribution network models and lack generalization and adaptability. Data-driven methods are promising for DER coordination but face practical challenges such as potential hazards to microgrids during online training and insufficient online training opportunities due to low outage rates. This paper presents a novel two-stage learning framework that builds on the deep deterministic policy gradient from demonstrations to identify an optimal restoration strategy. At the pre-training stage, imitation learning is applied to equip the control agent with expert experiences to guarantee acceptable initial performance. At the online training stage, action clipping, reward shaping, and expert demonstrations are leveraged to ensure safe exploration while accelerating the training process. In conclusion, the proposed method is illustrated using the IEEE 123-node system and compared with a representative model-based method and the standard deep deterministic policy gradient method to prove solution accuracy and demonstrate increased computational efficiency.

Du, Yan↗

DOE OSTI2024

Polymer Additive Manufacturing for Marine Renewable Energy Applications: Best Practices, Research Trends, and Current Challenges

Additive manufacturing (AM) is a rapidly growing technology space, not only for prototyping, but is also becoming more feasible at larger scales and increasing component quantities. There are a large variety of AM processes and materials available to users and effectively applying those processes and materials to a specific use case can be challenging. One specific area where AM could be particularly beneficial is marine renewable energy (MRE). Not only is MRE a relatively nascent industry with a near-term need for rapid deployments and prototype testing, but developers could also see long-term benefits from the broad variety of environmentally resistant materials available and the ability to manufacture complex geometries that AM technologies offer. Over the past 4 years, AM materials have played an increasing role in the Advanced Materials project; a multi-year, multi-laboratory research project funded by the U.S. Department of Energy's Water Power Technologies Office, with the main goal of reducing barriers to the adoption of complex materials in the MRE industry. The primary focus of this project is to develop test methods and generate datasets to understand the long-term performance of advanced materials in marine environmental and address specific material challenges as they arise. This report provides an extensive overview of the research that has been performed specific to AM polymers as part of the Advanced Materials project. The intention of this document is to provide recommendations of best practices with regards to material selection, mechanical test method development, and design practices, lessons learned along the way, current research trends, and ongoing challenges with regards to AM polymers in marine environments. In particular, this report focuses on several key aspects: Material and process selection, Environmental conditioning and subsequent degradation quantification through mechanical characterization, Composite reinforcements on AM polymer substrates, Adhesion of instrumentation for mechanical characterization and loads measurements, Protective coatings for preventing biofouling and water ingress, Other MRE case studies where AM has proved particularly useful. Ultimately, we hope that the test methods that have been developed, data generated, and lessons learned from this research will be valuable to the MRE community (researchers and developers alike), as well as other industries, and can be used as a reference point as the respective MRE and AM industries continue to grow and mature.

16 TIDAL AND WAVE POWER↗