Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “agent based model”

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 397 records · Page 22
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Evaluating the Adaptability of Reinforcement Learning Based HVAC Control for Residential Houses

Intelligent Heating, Ventilation, and Air Conditioning (HVAC) control using deep reinforcement learning (DRL) has recently gained a lot of attention due to its ability to optimally control the complex behavior of the HVAC system. However, more exploration is needed on understanding the adaptability challenges that the DRL agent could face during the deployment phase. Using online learning for such applications is not realistic due to the long learning period and likely poor comfort control during the learning process. Alternatively, DRL can be pre-trained using a building model prior to deployment. However, developing an accurate building model for every house and deploying a pre-trained DRL model for HVAC control would not be cost-effective. In this study, we focus on evaluating the ability of DRL-based HVAC control to provide cost savings when pre-trained on one building model and deployed on different house models with varying user comforts. We observed around 30% of cost reduction by pre-trained model over baseline when validated in a simulation environment and achieved up to 21% cost reduction when deployed in the real house. This finding provides experimental evidence that the pre-trained DRL has the potential to adapt to different house environments and comfort settings.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2022

A Hybrid Reinforcement Learning-MPC Approach for Distribution System Critical Load Restoration: Preprint

This paper proposes a hybrid control approach for distribution system critical load restoration, combining deep reinforcement learning (RL) and model predictive control (MPC) aiming at maximizing total restored load following an extreme event. RL determines a policy for quantifying operating reserve requirements, thereby hedging against uncertainty, while MPC models grid operations incorporating RL policy actions, i.e., the reserve requirement, renewable (wind and solar) power predictions, and load demand forecasts. We formulate the reserve requirement determination problem as a sequential decision making problem based on the Markov Decision Process (MDP) and design an RL learning environment based on the OpenAI Gym framework and MPC. The RL agent reward and MPC objective function aim to maximize and monotonically increase total restored load and minimize load shedding and renewable power curtailment. The RL algorithm is trained off-line using historical forecast of renewable generation and load demand. The method is tested using a modified IEEE 13-bus distribution test feeder containing wind turbine, photovoltaic, microturbine and battery. Case studies demonstrated that the proposed method outperforms other operating reserve determination methods.

distribution system↗
DOE OSTI2023

Stability study of aqueous foams under high-temperature and high-pressure conditions relevant to Enhanced Geothermal Systems (EGS)

In Enhanced Geothermal System (EGS) hydraulic fracturing is carried out by injecting cold water into deep Hot Dry Rocks (HDR) under carefully controlled conditions to create new or reopen existing fractures. Water-based fracturing fluids demonstrate some challenges including immense quantity of water usage, water sensitivity of the formations, water blocking, and lack of proppant carrying capacity and transportation. Thus, an alternative is to use foam-based fracturing fluid which offers potential advantage over conventional water-based fracturing fluid such as minimum water usage, reduced wellbore damage, high proppant carrying capacity, and less environmental damage. However, foams are complex mixture of gaseous phase and liquid phase which are thermodynamically unstable at downhole conditions, and their stability can decrease over time due to liquid drainage, bubble coarsening, and coalescence. This paper shows laboratory experiments executed to study foam stability at high temperature (200°C) and high pressure (6.9MPa) conditions which simulates the geothermal environment. Foam stability was characterized by half-life of foam, which is defined as the time taken by the foam to decreases by 50% of its original height due to drainage. In this paper, two types of gaseous phases, nitrogen (N 2 ) and carbon dioxide (CO 2 ) were investigated. Also, based on successful practice of foam-based fracturing fluid in oil and gas industries, four surfactants, including Alpha olefin sulfonate (AOS), Sodium dodecyl sulfonate (SDS), Tergitol™ (NP – 40), and Cetyltrimethylammonium chloride (CTAC) at optimum concentration of 1wt.% were tested for best stability performance. In addition, different stabilizing agents including guar gum, bentonite clay, crosslinker, silicon dioxide nanoparticles (SiO 2 ), graphene oxide (GO) were also studied. Experimental results showed that N 2 foams were more stable than CO 2 foams. It was observed that foam half-life decreased with the increase in temperature. Among all the surfactants, AOS foams showed the most promising thermal stability at high temperatures. Moreover, with the addition of stabilizing agents, foam's half-life was enhanced. Stabilizing agents such as crosslinker and GO dispersion showed the most stable foams with half-life recorded at 20min and 17min, respectively, at 200°C and 6.9MPa. Finally, pressure also showed a positive effect on foam stability; with increased pressure, foam half-life was increased. Based on the experimental data, analytical models for the effect of temperature and pressure were developed, considering foam degradation is a first-order kinetic reaction that linearly depends on the foam drainage mechanism. The effect of temperature on foam half-life was studied as an exponential decay model. In this model, foam half-life is a function of drainage rate constant (D A ) and activation energy (E a ) of the foam system. The effect of pressure on foam half-life was found to obey a power-law model where an increase in pressure showed an increase in foam half-life. Furthermore, a linear relation was studied for the effect of pressure on foam activation energy and drainage rate. Then the combined effects of temperature and pressure were studied, which yielded an analytical model to predict the foam stabilities in terms of half-life for different foam compositions. In conclusion, this research indicates that with an appropriate selection of surfactants and stabilizing agents, it is possible to obtain stable foams, which could replace conventional water fracturing fluid under EGS conditions.

15 GEOTHERMAL ENERGY↗
DOE OSTI2025

Holistic Microstructure Control Strategies in Photopolymerization‐Induced Phase Separation of Acrylate Systems

Open porous materials, known for their large surface area and interconnected structures, are essential in various applications, including batteries, ion exchange, catalysis, filtration, and electronic waste recycling. A critical aspect of the functionality of porous membranes is the precise control of pore size and morphology. Photopolymerization-induced phase separation (photo-PIPS) offers a convenient and versatile methods for creating porous structures. However, controlling the porous morphology remains challenging due to the complex interplay between thermodynamics, polymerization kinetics, and monomer structures, which makes it difficult to establish the relationship between processing conditions and resulting morphology in photo-PIPS. Herein, a physics-based phase-field model capable of generating and characterizing the microstructures of porous materials based on both average and localized features is developed. Using the phase-field simulations as test bed, the effects of polarity, light intensity, and curing temperature, as well as the previously unexplored roles of chain transfer agents and substrates, on the morphology of the resulting porous microstructure are investigated. Experiments are performed to verify the results predicted by the simulations. This work lays out a comprehensive guide for designing PIPS-derived porous microstructures and offers practical engineering strategies for tailoring microstructure-level topology and size of pores for application-specific needs.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Hamilton: Flexible, Open Source $10 Wireless Sensor System for Energy Efficient Building Operation

Sensors for improving building performance are rapidly populating the market, driven in part by the drive to reduce greenhouse gas emissions resulting from energy production as well as improve the interior environment for healthy and more productive spaces. UC Berkeley has led wireless sensor development over the past 25 years (e.g., Telos mote), with the Hamilton (named after Alexander Hamilton on the US $10 bill) as the most recent. The Hamilton sensor was designed as a low-cost high-performance sensor that is modular and interoperable. The objective of the Hamilton project was to create, evaluate and establish the technological foundations for secure and easy to deploy building energy efficiency applications utilizing pervasive, low-cost wireless sensors integrated with traditional Building Management Systems (BMS), consumer-sector building components, and powerful data analytics. The project included iterative hardware design, incorporating a high-performance database (BTrDb, http://btrdb.io/), creating and iterating the development of secure data middleware (BOSSwave, WAVE/WAVEMQ), working with and pushing the development of an open-source tiny operating system RiotOS, and implementing and improving protocols such as Thread/OpenThread and TCP/IP. The hardware benefited from careful design to drive down the cost; the design included a System-on-a-Chip (SoC), chip antenna, single crystal and five passive components. Careful design of the operating system created a low-power design to enable a long life with small batteries. The hardware included several sensors: temperature, radiant temperature, relative humidity, magnetometer, accelerometer, and light, with an optional occupancy (Passive InfraRed) sensor. The project was the basis of several applications, both internal to the research team and other researchers and professionals at other institutions. Several applications used the sensor hardware as the basis for other complex devices. Other applications used the sensors to improve building performance through interoperating with the building Heating Ventilation and Air-Conditioning (HVAC) system, such as using occupancy and/or distributed temperature sensing to reduce HVAC zone energy while still providing thermal comfort and to reduce peak loads in small commercial buildings. We demonstrated cloud-based energy analytics, implemented a schedule and a Model Predictive Controller in a small commercial building to optimize HVAC energy, occupancy and electricity price. Initial integration of these technological innovations was performed through the creation of execution containers containing the WAVE agent and various driver, proxy, or building system function logic. The research added to the understanding of efficient sensor hardware, secure middleware, time-series data management (high performance database), efficient communication protocols, and interoperating with applications and building systems. The project showed the technical effectiveness and economic feasibility of creating a low-cost, modular, and easy-to-deploy sensor. Through conversations with multiple end users, the research team discovered that many customers wanted data management and services in addition to the sensors. HamiltonIOT developed packages of sensors, border router, and data services to provide a seamless “plug-and-play” sensor deployment. Some customers were willing to pay for higher quality sensors (such as light); some customers wanted a robust enclosure (waterproof).

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2022

A Hybrid Reinforcement Learning-MPC Approach for Distribution System Critical Load Restoration

This paper proposes a hybrid control approach for distribution system critical load restoration, combining deep reinforcement learning (RL) and model predictive control (MPC) aiming at maximizing total restored load following an extreme event. RL determines a policy for quantifying operating reserve requirements, thereby hedging against uncertainty, while MPC models grid operations incorporating RL policy actions (i.e., reserve requirements), renewable (wind and solar) power predictions, and load demand forecasts. We formulate the reserve requirement determination problem as a sequential decision-making problem based on the Markov Decision Process (MDP) and design an RL learning environment based on the OpenAI Gym framework and MPC simulation. The RL agent reward and MPC objective function aim to maximize and monotonically increase total restored load and minimize load shedding and renewable power curtailment. The RL algorithm is trained offline using a historical forecast of renewable generation and load demand. The method is tested using a modified IEEE 13-bus distribution test feeder containing wind turbine, photovoltaic, microturbine, and battery. Case studies demonstrated that the proposed method outperforms other policies with static operating reserves.

distribution system↗
DOE OSTI2020

Reinforcement learning based automated history matching for improved hydrocarbon production forecast

History matching aims to find a numerical reservoir model that can be used to predict the reservoir performance. An engineer and model calibration (data inversion) method are required to adjust various parameters/properties of the numerical model in order to match the reservoir production history. In this study, we develop deep neural networks within the reinforcement learning framework to achieve automated history matching that will reduce engineers’ efforts, human bias, automatically and intelligently explore the parameter space, and remove the need of large set of labeled training data. To that end, a fast-marching-based reservoir simulator is encapsulated as an environment for the proposed reinforcement learning. The deep neural-network-based learning agent interacts with the reservoir simulator within reinforcement learning framework to achieve the automated history matching. Reinforcement learning techniques, such as discrete Deep Q Network and continuous Deep Deterministic Policy Gradients, are used toth, used to train the learning agents. The continuous actions enable the Deep Deterministic Policy Gradients to explore more states at each iteration in a a learning episode; consequently, a better history matching is achieved using this algorithm as compared to Deep Q Network. For simplified dual-target composite reservoir models, the best history-matching performances of the discrete and continuous learning methods in terms of normalized root mean square errors are 0.0447 and 0.0038, respectively. Furthermore, our study shows that continuous action space achieved by the deep deterministic policy gradient drastically outperforms deep Q network.

42 ENGINEERING↗
DOE OSTI2022

The development and use of decision support framework for informing selection of select agent toxins with modelling studies to inform permissible toxin amounts

Many countries have worked diligently to establish and implement policies and processes to regulate high consequence pathogens and toxins that could have a significant public health impact if misused. In the United States, the Antiterrorism and Effective Death Penalty Act of 1996 (Public Law 104-132, 1996), as amended by the Bioterrorism Preparedness and Response Act of 2002 (Public Law 107-188, 2002) requires that the Department of Health and Human Services (HHS) [through the Centers for Disease Control and Prevention (CDC)] establish a list of bacteria, viruses, and toxins that have the potential to pose a severe threat to public health and safety. Currently, this list is reviewed and updated on a biennial basis using input from subject matter experts (SMEs). We have developed decision support framework (DSF) approaches to facilitate selection of select toxins and, where toxicity data are known, conducted modelling studies to inform selection of toxin amounts that should be excluded from select agent regulations. Exclusion limits allow laboratories to possess toxins under an established limit to support their research or teaching activities without the requirement to register with the Federal Select Agent Program. Fact sheets capturing data from a previously vetted SME workshop convened by CDC, literature review and SME input were developed to assist in evaluating toxins using the DSF approach. The output of the DSF analysis agrees with the current select toxin designations, and no other toxins evaluated in this study were recommended for inclusion on the select agent and toxin list. To inform the selection of exclusion limits, attack scenarios were developed to estimate the amount of toxin needed to impact public health. Scenarios consisted of simulated aerosol releases of a toxin in high-population-density public facilities and the introduction of a toxin into a daily consumable product supply chain. Using published inhalation and ingestion median toxic dose (TD 50 ) and median lethal dose (LD 50 ) values, where available, a range of toxin amounts was examined to estimate the number of people exposed to these amounts in these scenarios. Based on data generated by these models, we proposed toxin exclusion values corresponding to levels below those that would trigger a significant public health response (i.e., amounts estimated to expose up to ten people by inhalation or one hundred people by ingestion to LD 50 or TD 50 levels of toxin in the modeled scenarios).

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

A2SD: Accelerating Scientific Innovation Through Autonomous Discovery Systems

The 2025 Advancing Autonomous Scientific Discovery (A2SD) workshop convened researchers from academia, national laboratories, and industry to explore the transformative role of autonomy in scientific discovery. The workshop highlighted a convergence of artificial intelligence, robotics, and computational workflows into autonomous systems capable of accelerating the scientific process. Presentations and discussions spanned autonomous experimentation, intelligent workflow orchestration, digital twins, and agent-based systems for managing complex research ecosystems. Key challenges discussed included interoperability across heterogeneous infrastructures, near real-time data management under FAIR principles, reproducibility, and the integration of human oversight. The workshop also emphasized the need for modular software interfaces, federated learning models, and education initiatives to support a next-generation scientific workforce.

Taufer, Michela [University of Tennessee, Knoxvill↗
DOE OSTI2022

Enhanced Oblique Decision Tree Enabled Policy Extraction for Deep Reinforcement Learning in Power System Emergency Control

Deep reinforcement learning (DRL) algorithms have successfully solved many challenging problems in various power system control scenarios. However, their decision-making process is usually regarded as black-boxes. Furthermore, how DRL models interact with human intelligence remains an open problem. Thus, this paper proposes a policy extraction framework to extract a complex DRL model into an explainable policy. This framework includes three parts: 1) DRL training and data generation. We train an agent for a specific control task and generate data, which contains the control policy of the agent. 2) Policy extraction. We propose an information gain rate based weighted oblique decision tree (IGR-WODT) for DRL policy extraction. 3) Policy evaluation. We define three metrics to evaluate the performance of the proposed approach. A case study for the under-voltage load shedding problem shows that the IGR-WODT presents a performance enhancement compared with DRL, weighted oblique decision tree, and univariate decision tree. The proposed policy extraction method could provide an intuitive explanation of the neural network decision-making process to the dispatchers when making final decisions on power grid operation. Also, the resulted rule-based controller could replace the deep neural network-based controller in many field edge devices with limited computing resources, providing comparable performance.

deep reinforcement learning↗
DOE OSTI2026

Optimization and stabilization of Fermilab Booster using hybrid Bayesian/RL framework

PIPII project will raise Fermilab Booster intensity and ramp rate. Beam losses will limit average power and are hard to simulate. Presently, Booster uses operator-guided empirical tuning. This task is challenging due to high dimensionality, multiple objectives, critical safety constraints, and drifts. We developed a synergistic suite of Bayesian optimization (BO) and reinforcement learning (RL) tools to optimize and stabilize beam losses. First, active learning was used to build a rough model. Data was collected parasitically using two novel safety constraint types – nonlinear input space restrictions (based on optics model), and uncertainty constraints (to stop bad steps/beam aborts). We then applied online multi-objective BO with scalarized objectives and fitting to improve/rebalance losses, increasing safety margins by 25%. Using BO model as a safety veto, we tried several on/off-policy RL agents for long term stabilization; SAC had best performance. We found that adding contextual (state) information further improved performance, eventually integrating key knobs like linac phase and temperature into the parameter space. Long term testing is ongoing to enable operational use.

Kuklev, Nikita [Fermilab]↗
DOE OSTI2025

Distributed fiber-optic sensing in a subscale high-temperature superconducting dipole magnet

High-temperature superconductors, such as REBa2Cu3O7−x (REBCO, RE = rare earth), are becoming pivotal for high-field magnet technology for future circular colliders and compact fusion reactors. The U.S. Magnet Development Program, in collaboration with industry, is developing REBCO magnet technology using round conductors consisting of multiple REBCO tapes. For these multi-tape cables, traditional instrumentation, such as voltage taps and resistive strain gauges, become insufficient to help measure and understand the performance-limiting factors in these model magnets. Distributed fiber-optic sensing (DFOS) is a potential solution to address this challenge. Although DFOS is well established for various applications, measuring temperature and strain in high-temperature superconducting magnets is in its infancy. Here we report the detailed implementation and test results of DFOS based on Rayleigh scattering in a subscale canted cosθ (CCT) dipole magnet using high-temperature superconducting CORC® wires. We co-wound optical fibers in each layer of the CCT magnet and compared different types of commercial fibers and mold-release agents to reduce the power attenuation in the fibers. The DFOS allowed us to measure mechanical deformation and temperature along the conductor during tests at 77 and 4.2 K. The measured strain agreed quantitively with a finite-element mechanical model of the subscale magnet. Our results indicate that DFOS can effectively identify locations of strain and temperature changes, offering unique insight into magnet performance that can advance our understanding and development of the REBCO magnet technology for high-energy physics and fusion applications.

Luo, Linqing↗
DOE OSTI2026

GridCoPilot for Thermal Events: An LLM-Based Platform for Power Grid Reliability Analysis

Large Language Models show promise for translating natural language into database queries, but deploying such systems in safety-critical domains requires high reliability. We present an application of GridCoPilot to thermal event analysis (heatwaves and coldwaves) that affect power grid reliability. Our approach uses a LangChain SQL Agent to translate natural language queries into auditable SQL statements, with deterministic visualization routines that parse the structured query results. We introduce structural framing as a design principle, we integrate a NERC-region-level event library with county-level meteorology and decompose the combined data into three relational tables (event metadata, county-level event details, and a county-to-NERC subregion mapping), using prompt-guided joins to direct the model toward correct multi-table queries. For two core analytical patterns (identifying worst events by region and by region-year), the system achieved 100% SQL accuracy across all 16 NERC subregions and both event types (64 queries total). These results validate the approach for target use cases, though performance on diverse natural language formulations requires further investigation. We discuss design trade-offs, failure modes including JSON output truncation, and pathways for extending this approach to other hazard domains.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

Transactive Energy Systems: The Market-based Coordination of Distributed Energy Resources

This paper synthesizes a unifying framework that captures a large class of transactive energy systems studied in the literature. The framework consists of four key elements: agent preferences, control decisions, information structure, and solution concept. Among them, agent preference specifies the preferred outcome by each agent and models the conflict of interest in decision making. Control decision specifies the set of decisions for each agent to maximize its payoff. Information structure describes the information available to each agent before it makes a decision. Solution concept encodes the rationality assumptions of each agent in the system. These elements are important in identifying and distinguishing different transactive energy systems. In this paper, we use them to analyze a number of important ones, including the competitive equilibrium, Stackelberg game, reverse Stackelberg game, and mechanism design. Each class of these problems is formulated as a special case of the proposed transactive energy systems. Their connections and differences are discussed. Available tools and results for each category of problems are surveyed.

Li, Sen↗
DOE OSTI2023

Inverse reinforcement learning control for building energy management

Reinforcement learning (RL) based control is widely considered a promising approach in building automation and control as it has demonstrated the potential to deal with complex objectives in adjacent domains like robotics, autonomous vehicles, gaming applications, and advertisement recommendations. When applied to any environment, model-free RL learns to improve its control performance over time without requiring a control model, by receiving and then analyzing feedback from the building environment after each control action. Operational objectives are becoming increasingly complex through the simultaneous consideration of thermal comfort, carbon emissions, grid services, and indoor air quality. In this context, conventional rule-based control approaches are proving sub-optimal, mostly heuristic, and inadequate. The model-free and self learning nature of RL appears promising and attractive as it may address the scalability issues associated with advanced control approaches. However, it suffers from long training times and unstable control behavior during the early stages of its learning process, which makes it unsuitable to be applied directly to buildings. This paper addresses these issues using an inverse reinforcement learning approach (IRL), a technique utilized to learn the objective of a controller agent which is considered an expert in its respective domain. Here, we consider a rule-based control as the expert demonstrator. IRL is different from a direct imitation (i.e., direct mapping of states to actions) of control actions as it tries to find the underlying intent of an expert's policy, providing the controller with a better-generalized policy for unseen states or environments with slightly different dynamics. This approach propels the RL controller's policy to levels similar to or better than that of a rule-based policy before it starts learning by interacting with the building. This makes RL for building energy management applications more practical as it prevents the erratic and exploratory behavior in the initial training period, simultaneously speeding up the learning process when compared to applying an untrained RL agent directly to a building environment.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2020

OpenABLext: An automatic code generation framework for agent-based simulations on CPU-GPU-FPGA heterogeneous platforms

The execution of agent-based simulations (ABSs) on hardware accelerator devices such as graphics processing units (GPUs) has been shown to offer great performance potentials. However, in heterogeneous hardware environments, it can become increasingly difficult to find viable partitions of the simulation and provide implementations for different hardware devices. To automate this process, we present OpenABLext, an extension to OpenABL, a model specification language for ABSs. By providing a device-aware OpenCL backend, OpenABLext enables the co-execution of ABS on heterogeneous hardware platforms consisting of central processing units, GPUs, and field programmable gate arrays (FPGAs).We present a novel online dispatching method that efficiently profiles partitions of the simulation during run-time to optimize the hardware assignment while using the profiling results to advance the simulation itself. In addition, OpenABLext features automated conflict resolution based on user-specified rules, supports graph-based simulation spaces, and utilizes an efficient neighbor search algorithm. We show the improved performance of OpenABLext and demonstrate the potential of FPGAs in the context of ABS. We illustrate how co-execution can be used to further lower execution times. OpenABLext can be seen as an enabler to tap the computing power of heterogeneous hardware platforms for ABS.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Spatial Impacts of Electric Vehicle Charging on Power Grid Stability: A Downtown Atlanta Case Study

The rapid increase in electric vehicle (EV) charging demand poses a potential risk to power grid stability, particularly as the spatial distribution of this demand remains underexplored. Existing research often focuses on technical optimization models while overlooking the geographic and human dynamics that affect energy consumption. This study addresses this gap by incorporating mobility data to estimate both building energy use and EV charging demand while also considering geographic factors for a better understanding of grid load. Using agent-based simulations and the Open-Source Distribution System Simulator, the study evaluates the effect of various EV penetration scenarios on grid voltage and unbalance. The results show that, although voltage remains within acceptable limits at lower EV penetration rates, significant voltage drop and unbalance occur as EV penetration exceeds 40%, particularly in residential areas with high charging demand. This study offers a framework for integrating spatial analysis and mobility data in power network simulations, providing insights for future EV infrastructure planning.

Pan, Melrose [ORNL] (ORCID:000000031627448X)↗
DOE OSTI2023

3D_MolGNN_RL

3D-MolGNNRL, couples reinforcement learning (RL) to a deep generative model based on 3D-Scaffold to generate target candidates specific to a protein pocket building up atom by atom from the core scaffold. 3D-MolGNNRL provides an efficient way to optimize key features within a protein pocket using a parallel graph neural network model. The agent learns to build molecules in 3D space while optimizing the binding affinity, potency, and synthetic accessibility of the candidates generated for the SARS-CoV-2 Main protease

Kumar, Neeraj↗