Search NASA⌕ Search

SEARCH · Search NASA

Results for “multi-agent 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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Optimal CO 2 storage management considering safety constraints in multi-stakeholder multi-site GCS projects: A Markov game perspective

Geological carbon storage (GCS) projects could involve a diverse array of stakeholders or players from public, private, and regulatory sectors, each with different objectives and responsibilities. Given the complexity, scale, and long-term nature of GCS operations, determining whether individual stakeholders can independently optimize their interests — or whether collaborative coalition agreements are needed — remains a central question for effective GCS project planning and management. To access large, high-quality storage resources, future GCS deployment may increasingly occur in geologically connected sites, where shared geological features such as pressure space and reservoir pore capacity can lead to competitive behavior among stakeholders. In this work, we propose a paradigm based on Markov games to quantitatively investigate how different coalition structures affect the goals of stakeholders. We frame this multi-stakeholder multi-site problem as a multi-agent reinforcement learning problem with safety constraints. Our approach enables agents to learn optimal strategies while complying with safety regulations. We present an example where multiple operators are injecting CO 2 into their respective project areas in a geologically connected basin. To address the high computational cost of repeated simulations of high fidelity models, a previously developed surrogate model based on the Embed-to-Control (E2C) framework is employed. Our results demonstrate the effectiveness of the proposed framework in addressing optimal management of CO 2 storage when multiple stakeholders with different objectives and goals are involved.

58 GEOSCIENCES↗
DOE OSTI2024

Reinforcement Learning to Enhance Optimal Operation of Resilient Community Energy Systems

This paper presents a novel model-free multi-agent Reinforcement Learning (RL) control method to enhance the resilience of community energy systems in island mode, which coordinates multiple objectives without the necessity of identifying system models that require expert knowledge. Specifically, a community-level coordinator agent is designed to allocate renewable energy resources among different buildings, and multiple building-level agents are developed to optimize load schedules based on limited energy resources and requirements of building loads and occupants’ comfort. In a two-day evaluation, our RL approach demonstrated a similar performance against MPC without requiring system models and formulation of optimization problems as required in MPC.

ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION↗
DOE OSTI2024

PPO And Friends

PPO and Friends (PPOAF) is a pytorch implementation of proximal policy optimization for single- and multi-agent reinforcement learning (the PPO), along with several optimizations and add-ons (the Friends) to enable efficient MPI-parallelized model training on HPC clusters.

Maguire, AlisterO↗
DOE OSTI2024

Multi-Agent Graph-Attention Deep Reinforcement Learning for Post-Contingency Grid Emergency Voltage Control

Grid emergency voltage control (GEVC) is paramount in electric power systems to improve voltage stability and prevent cascading outages and blackouts in case of contingencies. While most deep reinforcement learning (DRL)-based paradigms perform single agents in a static environment, real-world agents for GEVC are expected to cooperate in a dynamically shifting grid. Moreover, due to high uncertainties from combinatory natures of various contingencies and load consumption, along with the complexity of dynamic grid operation, the data efficiency and control performance of the existing DRL-based methods are challenged. To address these limitations, we propose a multi-agent graph-attention (GATT)-based DRL algorithm for GEVC in multi-area power systems. Here, we develop graph convolutional network (GCN)-based agents for feature representation of the graph-structured voltages to improve the decision accuracy in a data-efficient manner. Furthermore, a cutting-edge attention mechanism concentrates on effective information sharing among multiple agents, synergizing different-sized subnetworks in the grid for cooperative learning. We address several key challenges in the existing DRL-based GEVC approaches, including low scalability and poor stability against high uncertainties. Test results in the IEEE benchmark system verify the advantages of the proposed method over several recent multi-agent DRL-based algorithms.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Multi-scale, Multi-disciplinary, and Multi-agent Explainable AI with Koopman-Undergirded Learning, Prediction, and Analysis (M3EA KULPA) (Project Closeout Report)

The goal of this project was to develop and use domain-aware machine learning formulations, based on the Koopman Operator (KO), for modelling multi-scale, multi-disciplinary (e.g., multi-physics), and/or multi-agent systems. The project developed these formulations for the following cases: • Systems with dynamics at two separate time scales, • Systems with a bi-level hierarchical control structure, • Systems with bi-level hierarchical control and dynamics at two separate time scales (the lower level controls operating at the faster time scale), and • Systems with n separate but interacting agents/disciplines (with/without control, respectively); the controls for each agent could include bi-level hierarchical control and dynamics at two separate time scales as described above. The project then defined a set of dynamical systems consisting of different nonlinear oscillators that could be used to test these different formulations and then subsequently learned the KO models for those systems. With the KO models, we were able to do the following: • Quantify system stability, including both long-term and transient behavior, • Quantify the effects of feedbacks between the different time scales and agents/disciplines in terms of those feedbacks’ effects on system stability, • Replace a standard Proportional-Integral (PI) control in the hierarchical control structure with a KO-based Linear-Quadratic Regular (LQR), a form of optimal control, • Calculate optimal supervisory control policies a) with and without time scale separated dynamics at the lower level control levels and b) with both PI and KO-based LQR lower level control policies, and • Calculate dynamic Nash equilibria for multi-agent systems where each agent makes its own control decisions.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Energy Optimization of Light and Heavy-Duty Vehicle Cohorts of Mixed Connectivity, Automation and Propulsion System Capabilities via Meshed V2V-V2I and Expanded Data Sharing (Final Scientific and Technical Report)

Vehicle connectivity and automated driving technologies individually have the potential to decrease energy consumption and/or increase safety on light, medium or heavy duty vehicles to varying degrees depending on the traffic infrastructure and specific driving scenarios. Due to advances in sensing, perception and computing power, research and development emphasis in the mobility sector has shifted away from connectivity. Prior research has shown that driving automation with the absence of connectivity can in certain circumstances increase energy consumption. The effectiveness of synergizing connectivity and driving automation technologies is the focus of this work, specifically applied to vehicle cohorts of mixed composition, light and heavy duty, and powertrains ranging from all electric to conventional internal combustion engine. The project team is led by Michigan Technological University (MTU) and partnered with AVL Mobility Technologies Inc. (AVL), Borg Warner (BW), Traffic Technology Services (TTS), American Center for Mobility (ACM) and Navistar (NAV). The main thrusts for the team are to develop a micro-traffic simulation environment with specific VD&PT system attributes and CAV capabilities, 2) field a vehicle test fleet of mixed classification, propulsion and CAV capacity, 3) develop artificial intelligence (AI) and machine learning (ML) based multi-agent optimization methods for various traffic infrastructures, 4) integrate the virtual environment and the optimization methods then deploy the system as a CAV hardware in the loop (HiL) for the vehicle test fleet and 5) conduct closed track and public road testing to validate simulation and demonstrated energy and mobility improvements at multiple scales. For a cohort of mixed vehicles, the team will demonstrate a reduction of energy consumption of 10-50% at intersection, arterial roadway and limited access highway scenarios through connectivity and automation in simulation and at a closed test track. The energy reduction objectives of the project are summarized in Table 1, indicating the infrastructure and over what distances are relevant considered. Single scenario energy reductions are not relevant and thus, the research team took the approach to vary parameters associated with the infrastructure, vehicle cohort composition and dynamic behavior to generate energy consumption distributions for both unconnected and connected scenarios.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2025

CyRRL (Cyber Resilient Reinforcement Learning for grid voltage control) [SWR-24-115]

This codebase contains a multi-agent, actor-critic reinforcement learning implementation for cyber-resilient grid voltage control. It uses a 123-bus OpenDSS system as the environment, with three-phase power flow translating nodal power injections into solved nodal voltages. The reward function penalizes deviations from nominal voltage as well as reactive power dispatch, while encouraging agents to take actions that result in fast convergence to nominal conditions. The codebase models false data injection attacks and includes functionality for training, testing, hyper-parameter tuning, and visualization.

Murphy, Sinnott [National Renewable Energy Laborat↗
DOE OSTI2024

Multi-agent voltage control in distribution systems using GAN-DRL-based approach

Active distribution grids can experience voltage fluctuations and violations due to the high penetration of variable distributed energy resources (DERs). These problems might occur because of the uncertain and variable generation natures of these resources, especially solar photovoltaic resources, during panel shadowing scenarios. Volt-VAR control (VVC) is an efficient method that controls the reactive power set-points of the inverters to regulate the voltage of distribution grids. Although several VVC approaches have been proposed recently, the performance of these approaches degrades significantly if behind-the-meter solar generation data are unobservable/missing. Therefore, it is necessary to impute missing/unobservable PV data accurately to be utilized in VVC approaches. Further, this paper proposes a model-free, data-driven, centrally trained, and decentrally executed multi-agent deep reinforcement learning-based VVC architecture to regulate the voltage of distribution networks. A generative adversarial network (GAN) is incorporated to impute the unobservable PV data accurately, which improves the performance of the proposed control architecture. The proposed multi-agent-soft-actor–critic algorithm (MASAC)-based VVC technique utilizes the actual PV dataset as well as the imputed dataset from the GAN framework to learn the optimal coordinated control policy for controlling the optimal reactive power set-points of PV inverters. The effectiveness of the proposed approach is analyzed on a modified IEEE 34-bus test case with added PV inverters. The results are compared and analyzed with a base case model with no VVC and VVC with a local droop control approach, genetic algorithm optimization, and a centralized soft actor–critic-based approach. Moreover, the performance of the proposed approach is compared with that of a multi-agent VVC framework without using the PV generation data and load information as the system state. The results illustrate that the proposed method with more state input improves the voltage profile and reduces the power loss of the network across various loading and PV generation scenarios.

14 SOLAR ENERGY↗
DOE OSTI2025

A Novel LDPP-MADDPG Approach for Distributed Power Allocation in mmWave Cellular Networks

This paper considers the problem of distributed beam scheduling and power allocation problem in millimeter- Wave (mmWave) cellular networks, in which multiple Base Stations (BSs) operate as individual operators over a shared spectrum. We propose a novel learning-aided approach that integrates the Lyapunov Drift-Plus-Penalty (LDPP) framework and Multi-agent Deep Deterministic Policy Gradient (MADDPG) reinforcement learning algorithms. This offers a powerful approach to learning stable and constraint-aware policies, reaping the joint benefit of both LDPP and MADDPG, in complex multiagent environments. The major challenge for this approach is to integrate these two approaches in a meaningful and effective manner. The key idea to solve this problem is to introduce a novel feature of local observation that incorporates potential negative value of the reward function due to the stochastic constraints introduced by the LDPP framework. Empirical results demonstrate that our proposed scheme outperforms the baseline methods under various conditions.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2026

Managing autonomous materials labs with multi-agent AI and its implications for the science of science

Self-driving lab systems (aka, autonomous experimentation) accelerate research - letting scientists learn faster, spend less resources, and fail smarter in well defined, narrow studies. The next-generation materials lab combines self-driving systems to tackle broader challenges - orchestrating complex research campaigns while optimizing lab resources. We propose that agent-based and agentic artificial intelligence will be an integral part of next-generation lab management and discuss potential implementation scenarios. Additionally, digital and physical sandboxes will allow scientists to evaluate diverse and dynamic research and lab management strategies. Beyond the immediate benefit to lab optimization, such sandboxes will enable realistic computational studies of the philosophy of science (i.e., science of science) to achieve higher level scientific efficiencies.

Computer science↗
DOE OSTI2026

Hierarchical Multi-agent Large Language Model Reasoning for Autonomous Heterogeneous Catalyst Discovery

Artificial intelligence is reshaping scientific exploration, but most methods automate procedural tasks without engaging in scientific reasoning, limiting autonomy in discovery. We demonstrate that hierarchical agentic large language model reasoning can efficiently drive simulation and scientific exploration. Across two chemical applications, CO adsorption on Cu surface transition metal adatoms and on M–N–C catalysts, reasoning-guided exploration reduces required atomistic simulations by up to 90% relative to heuristic or random selection. Comparisons across single-agent, multi-agent, and stochastic baselines show that hierarchical strategies yield more coherent and information-efficient search trajectories. Reasoning traces reveal chemically grounded decisions that cannot be explained by semantic bias or stochastic sampling. We realize these agentic reasoning strategies in Materials Agents for Simulation and Theory in Electronic-structure Reasoning (MASTER), a multimodal system that translates natural language into density functional theory workflows. Altogether, multi-agent collaboration accelerates heterogeneous catalyst discovery and marks a step toward more autonomous, reasoning-guided scientific exploration.

30 DIRECT ENERGY CONVERSION↗
DOE OSTI2026

matsim-agents v1.0

matsim-agents is a multi-agent AI framework for atomistic materials simulation and discovery. It orchestrates large language models (LLMs), machine-learned interatomic potentials (MLIPs), and DFT codes into a single agentic loop running on laptops and DOE leadership-class supercomputers. MULTI-AGENT ORCHESTRATION A LangGraph state machine with three nodes: a Planner that converts a natural-language research objective into structured tasks; an Executor that dispatches atomistic tools and loops until the queue is empty; and an Analyst that summarizes results into a human-readable report. State is checkpointed after every step and human-in-the-loop gates can be inserted at any edge. HYPOTHESIS-DRIVEN DISCOVERY CHAT An interactive REPL (matsim-agents chat) that couples LLM dialogue with atomistic simulation. Chemical formulas are automatically detected in conversation turns and trigger a full crystal-phase exploration: structure generation → relaxation → stability scoring → result injection back into the conversation, creating a closed hypothesis-refinement loop. CRYSTAL PHASE ENUMERATION Given a composition, the phase explorer enumerates prototypes by stoichiometry: elemental (fcc/bcc/hcp/sc/diamond), binary 1:1 (rocksalt/CsCl/zincblende/ wurtzite/fluorite/rutile), ternary 1:1:3 (cubic perovskite), ternary 1:2:4 (perovskite + spinel), quaternary 1:1:2:6 (Fm-3m double perovskite). 2-D prototypes (graphene, h-BN, MoS2 2H/1T) and multilayer stacking are also supported via --include-2d and --num-layers. SUPERCELL GENERATION AND SITE DECORATION Auto-tiling to a minimum atom count (--min-atoms), explicit NxNxN tiling (--supercell), symmetry-distinct site decorations (--n-orderings), and isotropic lattice-scale sweeps (--lattice-scales) for volume bracketing. MLFF RELAXATION AND STABILITY SCORING HydraGNN (multi-headed GNN) drives structure relaxation via ASE with FIRE, BFGS, or BFGSLineSearch. Stability output: delta-E/atom ranking across phases and a max-residual-force dynamical-stability proxy. Other MLIPs (MACE, NequIP, Orb) can be plugged in through the same interface. DFT BACKENDS Quantum ESPRESSO pw.x and VASP 6.6 are first-class labellers. Both have validated GPU builds and SLURM/PBS launchers for three DOE platforms: Frontier (AMD MI250X, ROCm), Aurora (Intel PVC, oneAPI), Perlmutter (NVIDIA A100, CUDA). QE produces ~100 binaries (pw.x, ph.x, epw.x, ...). VASP supports scf, relax, vc-relax, and vc-relax-shape run types. ACTIVE-LEARNING LOOP matsim-agents al run CONFIG.yaml drives an iterative HydraGNN-DFT loop: MD generates candidates → ensemble/MC-dropout uncertainty selects the most informative → DFT labels them in parallel inside one allocation → dataset grows → HydraGNN retrains → repeat. DFT backend is a single YAML toggle (dft.backend: vasp | qe). LLM-generated seed structures are supported (no curated POSCAR library needed). Config uses ${VAR}, ${VAR:-default}, ${VAR:?msg} shell-style substitution for cross-user/cross-site portability. LLM BACKENDS Ollama (local, default), vLLM (HPC multi-GPU serving), OpenAI, Anthropic, HuggingFace Transformers+Accelerate. Selected at runtime via flag or env var with no code changes. HPC PORTABILITY Same Python entry points run on Frontier (ROCm 7.2), Aurora (oneAPI), and Perlmutter (CUDA 12). DFT and ML stacks are never co-loaded in the same shell; they couple through the scheduler and filesystem. Advanced multi-node launchers (serve, discovery-chat, single-relaxation, active-learning, QE warm-start) are provided for all three platforms. CODABENCH COMPETITION BUNDLE A self-contained benchmark: 159 atomistic test structures across 11 material classes, 5 tasks (formation energy, forces, ML relaxation, AI-DFT relaxation, phase stability ranking), public/private leaderboard split (30/70), and four ready-to-run baselines: MACE-MP-0, HydraGNN, UMA, AllScAIP.

Lupo Pasini, Massimiliano [Oak Ridge National Labo↗
DOE OSTI2023

Analysis of Building Model Forecasts using Autonomous HVAC Optimization System for Residential Neighborhood

Heating, ventilation, and air conditioning (HVAC) systems account for the highest share of home energy consumption in the United States. Optimized HVAC control can provide thermal improved comfort to the occupants, improve energy efficiency, reduce energy cost, and support grid services. In this paper, we discuss a multi-agent and cloud-based software framework that has been deployed in occupied residential neighborhood. This system enables automatic data collection, learning, optimization, and dispatches signals to neighborhood devices. HVAC optimization is based on model predictive control (MPC). Since the operational performance of MPC depends on model forecasting accuracy, it is crucial to evaluate the model continuously and modify or retrain it as necessary. In this research, we developed an automated workflow to evaluate the performance of temperature and power forecasts based on measured data in the real world. This will provide researchers with a deeper understanding of the model and how it can be improved.

Lebakula, Viswadeep↗
DOE OSTI2026

Wolf

The Workflow Orchestration Language Framework (WOLF) is an agentic framework grounded in natural language with an architecture inspired by reinforcement learning (RL)—designed to orchestrate, scale, and accelerate complex workflows. The concept of WOLF was born out of the very successful ASC Tri-lab Multi-Agent Design Assistant (MADA) project, but extends beyond its domain-specific design agents to provide a more general and extensible architecture. WOLF capitalizes on the lessons learned from MADA and is fully aligned with Sutton’s The Bitter Lesson—that the most enduring progress in AI comes from general-purpose methods that scale with computation, rather than narrow techniques built on domain-specific human knowledge. In this spirit, WOLF enables agents to autonomously learn workflows, capture strategies as reusable playbooks, and build a growing corpus of interpretable, auditable “wisdom artifacts.” These artifacts, expressed in natural language, bridge human and machine understanding while preserving adaptability and scalability as computational power continues to expand.

Boureima, Ismaeal↗
DOE OSTI2025

CityLearn v2: energy-flexible, resilient, occupant-centric, and carbon-aware management of grid-interactive communities

As more distributed energy resources become part of the demand-side infrastructure, quantifying their energy flexibility on a community scale is crucial. CityLearn v1 provided an environment for benchmarking control algorithms. However, there is no standardized environment utilizing realistic building-stock datasets for distributed energy resource control benchmarking without co-simulation or third-party frameworks. CityLearn v2 extends CityLearn v1 by providing a stand-alone simulation environment that leverages the End-Use Load Profiles for the U.S. Building Stock dataset to create grid-interactive communities for resilient, multi-agent, and objective control of distributed energy resources with dynamic occupant feedback. While the v1 environment used pre-simulated building thermal loads, the v2 environment uses data-driven thermal dynamics and eliminates the need for co-simulation with building energy performance software. This work details the v2 environment and provides application examples that use reinforcement learning control to manage battery energy storage system, vehicle-to-grid control, and thermal comfort during heat pump power modulation.

Nweye, Kingsley↗
DOE OSTI2024

Behavior, Energy, Autonomy, Mobility Modeling Framework (BEAM) v1.0

The Behavior, Energy, Autonomy, and Mobility (BEAM) model is an integrated, agent-based travel demand simulation framework. Individual agents express preferences through a utility- maximizing evolutionary algorithm that minimizes each individual’s cost and time spent traveling via diverse modal options, including the competition for scarce supply resources such as parking spaces and charging infrastructure. BEAM simulates the essential elements that compose a dynamic transportation system. From the road network, parking and charging infrastructure, to the transit system and a synthetic population with plans and preferences, the virtual system is an amalgamation of multiple spatially resolved layers that together represent an integrated transportation system. BEAM is an extension to the MATSim (Multi-Agent Transportation Simulation) model, where agents employ reinforcement learning across successive simulated days to maximize their personal utility through plan mutation (exploration) and selecting between previously executed plans (exploitation). The BEAM model shifts some of the behavioral emphasis in MATSim from across-day planning to within- day planning, where agents dynamically respond to the state of the system during the mobility simulation. In BEAM, agents can plan across all major modes of travel including driving, walking, biking, transit, and demand-responsive ride hailing. It is designed to integrate with other open source transportation models, such as ActivitySim.

Lazarus, Jessica↗
DOE OSTI2024

ReLIC: Full-Scale Realization of Reinforcement Learning for Infrastructure Control

Prior efforts have shown that deep reinforcement learning (DRL) may provide a new method for controlling networked power systems. Though successful, prior approaches have not yet demonstrated their behavior on systems of realistic scale. This effort examined multiple theoretical and technical approaches to allow a DRL model to operate over a system of 2,000 buses or more. We find that allowing the DRL models to run training episodes in parallel provides near limitless efficiency gains, allowing us to train successful agents to behave on our Kuramoto transmission model of up to 4,000 buses. We further show that we can expand our PowerWorld DRL implementation to systems of up to 25 buses but struggle to go beyond this limit due to PowerWorld’s inability to run multiple instances at once. Finally, we examine a multi-agent approach and find that it performs as well if not better than our existing centralized approach.

97 MATHEMATICS AND COMPUTING↗