Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “reinforcement 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.

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

At least 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

CDRL: Certification-Driven Reinforcement Learning for Neutrino Flavor Model Discovery

Many scientific discovery problems require searching combinatorial hypothesis spaces under complex domain constraints. Reinforcement learning (RL) offers a promising approach, but existing methods rely on scalar rewards that provide limited information about why candidate solutions fail, leading agents to repeatedly explore invalid regions. We introduce Certification-Driven Reinforcement Learning (CDRL), a framework that leverages structured feedback from symbolic reasoning tools. When a candidate violates domain constraints, these tools produce certificates identifying the actions responsible for failure. CDRL converts these certificates into reusable constraints that eliminate classes of invalid solutions and guide exploration toward valid regions. We evaluate CDRL on neutrino flavor model discovery in theoretical particle physics, where the hypothesis space exceeds $10^{26}$ possible models, and compare it with the state-of-the-art RL approach previously used for this task. Across three theory spaces, CDRL achieves up to 1.95$\times$ higher valid model rates and up to 6.33$\times$ higher neutrino model rates while evaluating up to 4$\times$ fewer candidates. We further extract 40 interpretable rules from search trajectories using a post-hoc decision-tree framework and show that reusing them as soft constraints yields gains of up to 2$\times$ in valid model rates and 3$\times$ in neutrino model discovery across all three theory spaces. These results suggest that CDRL uncovers reusable structure in combinatorial search spaces and provides a general framework for scientific model discovery.

Jha, Piyush [Georgia Tech., Atlanta; Georgia Tech]↗
DOE OSTI2021

Model-Free Voltage Control of Active Distribution System with PVs Using Surrogate Model-Based Deep Reinforcement Learning

Accurate knowledge of the distribution system topology and parameters is required to achieve good voltage control performance, but this is difficult to obtain in practice. This paper proposes a physical-model-free voltage control method based on a surrogate-model-enabled deep reinforcement learning approach. Specifically, a surrogate model is trained in a supervised manner using the recorded limited number of historical data to learn the relationship between the power injections and voltage fluctuations of each node. Then, the deep reinforcement learning algorithm is applied to learn an optimal control strategy from the experiences obtained by continuous interactions with the surrogate model. The proposed method can achieve physical-model-free control of unbalanced distribution network and inform real-time decisions to deal with fast voltage fluctuations caused by the rapid variation of PV generation. Simulation results on an unbalance IEEE 123-bus system show that the proposed method can achieve similar performance as that of perfect physical-model-based approaches while being advantageous over other traditional methods.

active distribution network↗
DOE OSTI2022

graphenv: a Python library for reinforcement learning on graph search spaces

Many important and challenging problems in combinatorial optimization (CO) can be expressed as graph search problems, in which graph vertices represent full or partial solutions and edges represent decisions that connect them. Graph structure not only introduces strong relational inductive biases for learning (Battaglia et al., 2018) - in this context, by providing a way to explicitly model the value of transitioning (along edges) between one search state (vertex) and the next - but lends itself to problems both with and without clearly defined algebraic structure. For example, classic CO problems on graphs such as the Traveling Salesman Problem (TSP) can be expressed as either pure graph search or integer programs. Other problems, however, such as molecular optimization, do no have concise algebraic formulations and yet are readily implemented as a graph search (V. et al., 2022; Zhou et al., 2019). Such "model-free" problems constitute a large fraction of modern reinforcement learning (RL) research owing to the fact that it is often much easier to write a forward simulation that expresses all of the state transitions and rewards, than to write down the precise mathematical expression of the full optimization problem. In the case of molecular optimization, for example, one can use domain knowledge alongside existing software libraries to model the effect of adding a single bond or atom to an existing but incomplete molecule, and let the RL algorithm build a model of how good a given decision is by "experiencing" the simulated environment many times through. In contrast, a model-based mathematical formulation that fully expresses all the chemical and physical constraints is intractable. In recent years, RL has emerged as an effective paradigm for optimizing searches over graphs and led to state-of-the-art heuristics for games like Go and chess, as well as for classical CO problems such as the TSP. This combination of graph search and RL, while powerful, requires non-trivial software to execute, especially when combining advanced state representations such as Graph Neural Networks (GNN) with scalable RL algorithms.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Grid-Interactive Building Control Via Reinforcement Learning

In this work, we present the proposed two-stage reinforcement learning approach for training building controllers to help buildings to participate in DR events. The original conference paper for this research idea can be found at https://www.nrel.gov/docs/fy21osti/78000.pdf.

building control↗
DOE OSTI2021

Reinforcement learning in discrete action space applied to inverse defect design

Abstract Reinforcement learning (RL) algorithms that include Monte Carlo Tree Search (MCTS) have found tremendous success in computer games such as Go, Shiga and Chess. Such learning algorithms have demonstrated super-human capabilities in navigating through an exhaustive discrete action search space. Motivated by their success in computer games, we demonstrate that RL can be applied to inverse materials design problems. We deploy RL for a representative case of the optimal atomic scale inverse design of extended defects via rearrangement of chalcogen (e.g. S) vacancies in 2D transition metal dichalcogenides (e.g. MoS 2 ). These defect rearrangements and their dynamics are important from the perspective of tunable phase transition in 2D materials i.e. 2H (semi-conducting) to 1T (metallic) in MoS 2 . We demonstrate the ability of MCTS interfaced with a reactive molecular dynamics simulator to efficiently sample the defect phase space and perform inverse design—starting from randomly distributed S vacancies, the optimal defect rearrangement of defects corresponds a line defect of S vacancies. We compare MCTS performance with evolutionary optimization i.e. genetic algorithms and show that MCTS converges to a better optimal solution (lower objective) and in fewer evaluations compared to GA. We also comprehensively evaluate and discuss the effect of MCTS hyperparameters on the convergence to solution. Overall, our study demonstrates the effectives of using RL approaches that operate in discrete action space for inverse defect design problems.

42 ENGINEERING↗
DOE OSTI2026

Demonstration of reconstruction-free static magnetic control of DIII-D plasma with deep reinforcement learning

This paper presents the development and experimental validation of a reinforcement learning (RL)-based magnetic controller on the DIII-D tokamak. The controller directly maps raw magnetic diagnostic signals to actuator commands, replacing the traditional isoflux control algorithm based on equilibrium reconstruction. Four RL controllers are trained using the Soft Actor–Critic algorithm with an asymmetric Actor–Critic architecture in the NSFsim simulator. All controllers are deployed in the DIII-D Plasma Control System and operated with a 4 kHz feedback loop. Two randomization strategies are evaluated during training: evolving kinetic profiles and fixed kinetic profiles within each episode. The latter approach is found to better capture experimental deviations in the current density profile and to provide overall improved control performance. Robust operation is demonstrated across heating power scans in both L- and H-mode plasmas, as well as during transient events such as L–H transitions and pellet injections. Control errors in plasma shape and radial position remained within 1.5–2.0 cm and 1 cm, respectively. A notable discrepancy was observed in the vertical X-point position, with errors of up to approximately 4 cm, attributed to the current density distribution mismatches between simulations and experiments.

DIII-D↗
DOE OSTI2022

Reinforcement learning for adaptive maintenance policy optimization under imperfect knowledge of the system degradation model and partial observability of system states

Maintenance policy optimization usually is faced with challenges that arise from an imperfect knowledge of system degradation models and from the partial observability of system degradation states. Here, this paper proposes a reinforcement learning method to address these two challenges for a class of maintenance problems with Markov degradation processes. The reinforcement learning approach consists of a learning component and a planning component. Using sequentially collected observations, at each step of decision-making the learning component improves the knowledge of system degradation in terms of the probability distributions of the transition rates based on sequential Bayesian inference. Using the updated transition rates, at each step of decision-making the maintenance policy optimization problem is then formulated as a partially observable Markov decision problem, and the planning component computes the optimal maintenance policy that maximizes the expected cumulative reward. The proposed method is illustrated using a numerical example with repair and inspection maintenance actions. The result shows that as more observations are collected, the learning component progressively learns the true system degradation process, and the planning component adjusts the optimal maintenance policy accordingly as well, which leads to increased reward.

42 ENGINEERING↗
DOE OSTI2023

Reinforcement Learning of Structured Stabilizing Control for Linear Systems With Unknown State Matrix

This paper delves into designing feedback control gains for a continuous-time linear quadratic regulator (LQR) problem that is constrained to certain predefined structure with unknown state matrix. We bring forth the ideas from reinforcement learning (RL) in conjunction with sufficient stability and performance guarantees in order to design these structured gains using the trajectory measurements of states and controls. Here we first formulate a model-based framework using dynamic programming (DP) to embed the structural constraint to the LQR gain computation in the continuous-time setting, and then subsequently, formulate a policy iteration RL algorithm that can alleviate the requirement of known state matrix in conjunction with maintaining the feedback gain structure. The design enables a distributed learning control design which is necessary for many large-scale cyber-physical systems. Theoretical guarantees are provided for stability and convergence of the structured reinforcement learning (SRL) algorithm. We validate our theoretical results with numerical simulations on a multi-agent networked linear time-invariant (LTI) dynamic system.

42 ENGINEERING↗
DOE OSTI2021

Deep reinforcement learning control of hydraulic fracturing

Hydraulic fracturing is a technique to extract oil and gas from shale formations, and obtaining a uniform proppant concentration along the fracture is key to its productivity. Recently, various model predictive control schemes have been proposed to achieve this objective. But such controllers require an accurate and computationally efficient model which is difficult to obtain given the complexity of the process and uncertainties in the rock formation properties. In this article, we design a model-free data-based reinforcement learning controller which learns an optimal control policy through interactions with the process. Deep reinforcement learning (DRL) controller is based on the Deep Deterministic Policy Gradient algorithm that combines Deep-Q-network with actor-critic framework. In addition, we utilize dimensionality reduction and transfer learning to quicken the learning process. We show that the controller learns an optimal policy to obtain uniform proppant concentration despite the complex nature of the process while satisfying various input constraints.

42 ENGINEERING↗
DOE OSTI2020

Controlling colloidal crystals via morphing energy landscapes and reinforcement learning

We report a feedback control method to remove grain boundaries and produce circular shaped colloidal crystals using morphing energy landscapes and reinforcement learning–based policies. We demonstrate this approach in optical microscopy and computer simulation experiments for colloidal particles in ac electric fields. First, we discover how tunable energy landscape shapes and orientations enhance grain boundary motion and crystal morphology relaxation. Next, reinforcement learning is used to develop an optimized control policy to actuate morphing energy landscapes to produce defect-free crystals orders of magnitude faster than natural relaxation times. Morphing energy landscapes mechanistically enable rapid crystal repair via anisotropic stresses to control defect and shape relaxation without melting. This method is scalable for up to at least N = 10 3 particles with mean process times scaling as N 0.5 . Further scalability is possible by controlling parallel local energy landscapes (e.g., periodic landscapes) to generate large-scale global defect-free hierarchical structures.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Graph Partitioning and Sparse Matrix Ordering using Reinforcement Learning and Graph Neural Networks

We present a novel method for graph partitioning, based on reinforcement learning and graph convolutional neural networks. Our approach is to recursively partition coarser representations of a given graph. The neural network is implemented using SAGE graph convolution layers, and trained using an advantage actor critic (A2C) agent. We present two variants, one for finding an edge separator that minimizes the normalized cut or quotient cut, and one that finds a small vertex separator. The vertex separators are then used to construct a nested dissection ordering to permute a sparse matrix so that its triangular factorization will incur less fill-in. The partitioning quality is compared with partitions obtained using METIS and SCOTCH, and the nested dissection ordering is evaluated in the sparse solver SuperLU. Our results show that the proposed method achieves similar partitioning quality as METIS and SCOTCH. Furthermore, the method generalizes across different classes of graphs, and works well on a variety of graphs from the SuiteSparse sparse matrix collection.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Development of algorithms for augmenting and replacing conventional process control using reinforcement learning

Here, this work seeks to allow for the online operation and training of model-free reinforcement learning (RL) agents but limit the risk to system equipment and personnel. The parallel implementation of RL alongside more conventional process control (CPC) allows for the RL algorithm to learn from CPC. The past performance of both methods are assessed on a continuous basis allowing for a transition from CPC to RL and, if needed, transitioning back to CPC from RL. This allows for the RL algorithm to slowly and safely assume control of the process without significant degradation in control performance. It is shown that the RL can derive a near optimal policy even when coupled with a suboptimal CPC. It is also demonstrated that the coupled RL-CPC algorithm learns at a faster rate than traditional RL methods of exploration while the algorithm’s performance does not deteriorate below CPC, even when exposed to an unknown operating condition.

30 DIRECT ENERGY CONVERSION↗
DOE OSTI2024

Surfactant-Specific AI-Driven Molecular Design: Integrating Generative Models, Predictive Modeling, and Reinforcement Learning for Tailored Surfactant Synthesis

Molecular design is a critical aspect of various scientific and industrial fields, where the properties of molecules hold significant importance. In this study, a 3-fold methodology design is presented that leverages the power of generative artificial intelligence (AI), predictive modeling, and reinforcement learning to create tailored molecules with desired properties. This model synergistically combines deep learning techniques with Self-Referencing Embedded Strings (SELFIES) molecular representation to build a generative model that generates valid molecules and a graphical neural network model that accurately forecasts molecular properties. The Variational Autoencoder (VAE) coupled with reinforcement learning helps refine molecule generation based on targeted attributes. Data from an experimental study involving surfactants were used to test the framework. A validation of the structural integrity of the molecules generated was conducted, and Tanimoto similarities were used to quantify the similarity and diversity between the original and generated molecular structures. Also, saliency maps for the generated surfactants were produced to identify the features explaining the property values. Lastly, molecular dynamics simulations were used to validate the stability of the generated molecules. The results showed that the proposed framework can effectively produce valid molecules within the set property threshold value.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Optimal Coordination of Electric Vehicles for Grid Services using Deep Reinforcement Learning

Recent research has shown the effectiveness of reinforcement learning (RL) in coordinating electric vehicles (EVs) with vehicle-to-grid capabilities for grid services. However, many of these studies rely on lookup table and deep Q-network techniques, which can be impractical when dealing with continuous states and actions. In addition, existing RL designs inadequately account for battery aging effects, EV user satisfaction, uncertain departure and arrival time, and trip distance, which may compromise effective coordination. This paper aims to bridge these gaps by developing an innovative deep deterministic policy gradient-based RL framework for optimal coordination of EVs. Case studies were carried out using a test system with 100 EVs, and numerical analysis results showed that the proposed RL framework can effectively coordinate EVs to maximize economic benefits and user satisfaction while ensuring the expected battery lifespan.

Das, Avijit↗
DOE OSTI2022

MPRL (Multi-Pulse Reinforcement Learning)

MPRL contains code for defining and deploying reinforcement learning control agents for multi-pulse, multi-fuel advanced compression ignition engines.

Wimer, Nicholas↗
DOE OSTI2024

Extreme Risk Mitigation in Reinforcement Learning using Extreme Value Theory

Risk-sensitive reinforcement learning (RL) has garnered significant attention in recent years due to the growing interest in deploying RL agents in real-world scenarios. A critical aspect of risk awareness involves modelling highly rare risk events (rewards) that could potentially lead to catastrophic outcomes. These infrequent occurrences present a formidable challenge for data-driven methods aiming to capture such risky events accurately. While risk-aware RL techniques do exist, they suffer from high variance estimation due to the inherent data scarcity. Our work proposes to enhance the resilience of RL agents when faced with very rare and risky events by focusing on refining the predictions of the extreme values predicted by the state-action value distribution. To achieve this, we formulate the extreme values of the state-action value function distribution as parameterized distributions, drawing inspiration from the principles of extreme value theory (EVT). We propose an extreme value theory based actor-critic approach, namely, Extreme Valued Actor-Critic (EVAC) which effectively addresses the issue of infrequent occurrence by leveraging EVT-based parameterization. Importantly, we theoretically demonstrate the advantages of employing these parameterized distributions in contrast to other risk-averse algorithms. Our evaluations show that the proposed method outperforms other risk averse RL algorithms on a diverse range of benchmark tasks, each encompassing distinct risk scenarios.

Wang, Yu↗
DOE OSTI2023

Reinforcement Learning for Load-balanced Parallel Particle Tracing

We explore an online reinforcement learning (RL) paradigm to dynamically optimize parallel particle tracing performance in distributed-memory systems. Our method combines three novel components: (1) a work donation algorithm, (2) a high-order workload estimation model, and (3) a communication cost model. First, we design an RL-based work donation algorithm. Our algorithm monitors workloads of processes and creates RL agents to donate data blocks and particles from high-workload processes to low-workload processes to minimize program execution time. The agents learn the donation strategy on the fly based on reward and cost functions designed to consider processes' workload changes and data transfer costs of donation actions. Second, we propose a workload estimation model, helping RL agents estimate the workload distribution of processes in future computations. Third, we design a communication cost model that considers both block and particle data exchange costs, helping RL agents make effective decisions with minimized communication costs. We demonstrate that our algorithm adapts to different flow behaviors in large-scale fluid dynamics, ocean, and weather simulation data. Our algorithm improves parallel particle tracing performance in terms of parallel efficiency, load balance, and costs of I/O and communication for evaluations with up to 16,384 processors.

Distributed and parallel particle tracing↗
DOE OSTI2023

Microgrid energy scheduling under uncertain extreme weather: Adaptation from parallelized reinforcement learning agents

Microgrids are useful solutions for integrating renewable energy resources and providing seamless green electricity to minimize carbon footprint. In recent years, extreme weather events happened often worldwide and caused significant economic and societal losses. Such events bring uncertainties to the microgrid energy scheduling problems and increase the challenges of microgrid operation. Traditional optimization approaches suffer from the inaccuracy of the uncertain microgrid model and the unseen events. Existing reinforcement learning (RL) - based approaches are also hampered by the limited generalization and the increasing computational burden when stochastic formulations are required to accommodate the uncertainties. This paper proposes a new parallelized reinforcement learning (PRL) method based on the probabilistic events to handle the microgrid energy uncertainties. Specifically, several local learning agents are employed to interact with pertinent microgrid environments in a distributed manner and report outcomes to the global agent, which will optimize microgrid energy resources online during extreme events. The stochastic microgrid energy optimization problem is reformulated to include all possible scenarios with probabilities. The advantage estimate functions of learning agents are designed with a backward sweep to transfer the outcomes to the value function updating process. Two simulation studies, stochastic optimization and online testing, are performed to compare with several existing RL approaches. Results substantiate that the proposed PRL method can achieve up to 20% optimization performance improvement with 4 and 28 times less computation cost than Q-learning with experience replay and multi-agent Q-learning approaches, respectively.

24 POWER TRANSMISSION AND DISTRIBUTION↗