Search NASA⌕ Search

SEARCH · Search NASA

Results for “multi-agent”

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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
NASA NTRS1999

A Survey of Collective Intelligence

This chapter presents the science of "COllective INtelligence" (COIN). A COIN is a large multi-agent systems where: i) the agents each run reinforcement learning (RL) algorithms; ii) there is little to no centralized communication or control; iii) there is a provided world utility function that, rates the possible histories of tile full system. Tile conventional approach to designing large distributed systems to optimize a world utility does not use agents running RL algorithms. Rather that approach begins with explicit modeling of the overall system's dynamics, followed by detailed hand-tuning of the interactions between the components to ensure that they "cooperate" as far as the world utility is concerned. This approach is labor-intensive, often results in highly non-robust systems, and usually results in design techniques that, have limited applicability. In contrast, with COINs we wish to solve the system design problems implicitly, via the 'adaptive' character of the RL algorithms of each of the agents. This COIN approach introduces an entirely new, profound design problem: Assuming the RL algorithms are able to achieve high rewards, what reward functions for the individual agents will, when pursued by those agents, result in high world utility? In other words, what reward functions will best ensure that we do not have phenomena like the tragedy of the commons, or Braess's paradox? Although still very young, the science of COINs has already resulted in successes in artificial domains, in particular in packet-routing, the leader-follower problem, and in variants of Arthur's "El Farol bar problem". It is expected that as it matures not only will COIN science expand greatly the range of tasks addressable by human engineers, but it will also provide much insight into already established scientific fields, such as economics, game theory, or population biology.

Wolpert, David H.↗
NASA NTRS2000

Optimal Reward Functions in Distributed Reinforcement Learning

We consider the design of multi-agent systems so as to optimize an overall world utility function when (1) those systems lack centralized communication and control, and (2) each agents runs a distinct Reinforcement Learning (RL) algorithm. A crucial issue in such design problems is to initialize/update each agent's private utility function, so as to induce best possible world utility. Traditional 'team game' solutions to this problem sidestep this issue and simply assign to each agent the world utility as its private utility function. In previous work we used the 'Collective Intelligence' framework to derive a better choice of private utility functions, one that results in world utility performance up to orders of magnitude superior to that ensuing from use of the team game utility. In this paper we extend these results. We derive the general class of private utility functions that both are easy for the individual agents to learn and that, if learned well, result in high world utility. We demonstrate experimentally that using these new utility functions can result in significantly improved performance over that of our previously proposed utility, over and above that previous utility's superiority to the conventional team game utility.

Wolpert, David H.↗
NASA NTRS2000

Human-Centered Design for the Personal Satellite Assistant

The Personal Satellite Assistant (PSA) is a softball-sized flying robot designed to operate autonomously onboard manned spacecraft in pressurized micro-gravity environments. We describe how the Brahms multi-agent modeling and simulation environment in conjunction with a KAoS agent teamwork approach can be used to support human-centered design for the PSA.

Bradshaw, Jeffrey M.↗
NASA NTRS2001

Learning Sequences of Actions in Collectives of Autonomous Agents

In this paper we focus on the problem of designing a collective of autonomous agents that individually learn sequences of actions such that the resultant sequence of joint actions achieves a predetermined global objective. We are particularly interested in instances of this problem where centralized control is either impossible or impractical. For single agent systems in similar domains, machine learning methods (e.g., reinforcement learners) have been successfully used. However, applying such solutions directly to multi-agent systems often proves problematic, as agents may work at cross-purposes, or have difficulty in evaluating their contribution to achievement of the global objective, or both. Accordingly, the crucial design step in multiagent systems centers on determining the private objectives of each agent so that as the agents strive for those objectives, the system reaches a good global solution. In this work we consider a version of this problem involving multiple autonomous agents in a grid world. We use concepts from collective intelligence to design goals for the agents that are 'aligned' with the global goal, and are 'learnable' in that agents can readily see how their behavior affects their utility. We show that reinforcement learning agents using those goals outperform both 'natural' extensions of single agent algorithms and global reinforcement, learning solutions based on 'team games'.

Turner, Kagan↗
NASA NTRS2003

Collectives for Multiple Resource Job Scheduling Across Heterogeneous Servers

Efficient management of large-scale, distributed data storage and processing systems is a major challenge for many computational applications. Many of these systems are characterized by multi-resource tasks processed across a heterogeneous network. Conventional approaches, such as load balancing, work well for centralized, single resource problems, but breakdown in the more general case. In addition, most approaches are often based on heuristics which do not directly attempt to optimize the world utility. In this paper, we propose an agent based control system using the theory of collectives. We configure the servers of our network with agents who make local job scheduling decisions. These decisions are based on local goals which are constructed to be aligned with the objective of optimizing the overall efficiency of the system. We demonstrate that multi-agent systems in which all the agents attempt to optimize the same global utility function (team game) only marginally outperform conventional load balancing. On the other hand, agents configured using collectives outperform both team games and load balancing (by up to four times for the latter), despite their distributed nature and their limited access to information.

Tumer, K.↗
NASA NTRS2003

Transition-Independent Decentralized Markov Decision Processes

There has been substantial progress with formal models for sequential decision making by individual agents using the Markov decision process (MDP). However, similar treatment of multi-agent systems is lacking. A recent complexity result, showing that solving decentralized MDPs is NEXP-hard, provides a partial explanation. To overcome this complexity barrier, we identify a general class of transition-independent decentralized MDPs that is widely applicable. The class consists of independent collaborating agents that are tied up by a global reward function that depends on both of their histories. We present a novel algorithm for solving this class of problems and examine its properties. The result is the first effective technique to solve optimally a class of decentralized MDPs. This lays the foundation for further work in this area on both exact and approximate solutions.

Becker, Raphen↗
NASA NTRS2001

Design and Control of Large Collections of Learning Agents

The intelligent control of multiple autonomous agents is an important yet difficult task. Previous methods used to address this problem have proved to be either too brittle, too hard to use, or not scalable to large systems. The 'Collective Intelligence' project at NASA/Ames provides an elegant, machine-learning approach to address these problems. This approach mathematically defines some essential properties that a reward system should have to promote coordinated behavior among reinforcement learners. This work has focused on creating additional key properties and algorithms within the mathematics of the Collective Intelligence framework. One of the additions will allow agents to learn more quickly, in a more coordinated manner. The other will let agents learn with less knowledge of their environment. These additions will allow the framework to be applied more easily, to a much larger domain of multi-agent problems.

Agogino, Adrian↗
NASA NTRS2003

INFUSION: Modeling Robot and Crew Interaction

Brahms is a multi-agent modeling and simulation language and distributed runtime system developed at NASA. It can be used to model and run a simualtion of the distributed work activities of multiple agents, such as humans,robots, and software agents, to coordinate a mission on one or more locations.Brahms is being used to model activities at the Flashline Man Arctic Research Station for possible use in planning Mars missions. The station is located at Haughton Crater, Devon Island, Nutiavut, Arctic Canada.

Laufenberg, Lawrence↗
NASA NTRS2001

Human Centered Autonomous and Assistant Systems Testbed for Exploration Operations

The Engineering and Mission Operations Directorates at NASA Johnson Space Center are combining laboratories and expertise to establish the Human Centered Autonomous and Assistant Systems Testbed for Exploration Operations. This is a testbed for human centered design, development and evaluation of intelligent autonomous and assistant systems that will be needed for human exploration and development of space. This project will improve human-centered analysis, design and evaluation methods for developing intelligent software. This software will support human-machine cognitive and collaborative activities in future interplanetary work environments where distributed computer and human agents cooperate. We are developing and evaluating prototype intelligent systems for distributed multi-agent mixed-initiative operations. The primary target domain is control of life support systems in a planetary base. Technical approaches will be evaluated for use during extended manned tests in the target domain, the Bioregenerative Advanced Life Support Systems Test Complex (BIO-Plex). A spinoff target domain is the International Space Station (ISS) Mission Control Center (MCC). Prodl}cts of this project include human-centered intelligent software technology, innovative human interface designs, and human-centered software development processes, methods and products. The testbed uses adjustable autonomy software and life support systems simulation models from the Adjustable Autonomy Testbed, to represent operations on the remote planet. Ground operations prototypes and concepts will be evaluated in the Exploration Planning and Operations Center (ExPOC) and Jupiter Facility.

Malin, Jane T.↗
NASA NTRS2001

Architectures and Evaluation for Adjustable Control Autonomy for Space-Based Life Support Systems

In the past five years, a number of automation applications for control of crew life support systems have been developed and evaluated in the Adjustable Autonomy Testbed at NASA's Johnson Space Center. This paper surveys progress on an adjustable autonomous control architecture for situations where software and human operators work together to manage anomalies and other system problems. When problems occur, the level of control autonomy can be adjusted, so that operators and software agents can work together on diagnosis and recovery. In 1997 adjustable autonomy software was developed to manage gas transfer and storage in a closed life support test. Four crewmembers lived and worked in a chamber for 91 days, with both air and water recycling. CO2 was converted to O2 by gas processing systems and wheat crops. With the automation software, significantly fewer hours were spent monitoring operations. System-level validation testing of the software by interactive hybrid simulation revealed problems both in software requirements and implementation. Since that time, we have been developing multi-agent approaches for automation software and human operators, to cooperatively control systems and manage problems. Each new capability has been tested and demonstrated in realistic dynamic anomaly scenarios, using the hybrid simulation tool.

Malin, Jane T.↗
NASA NTRS2000

Autonomous Agents and Intelligent Assistants for Exploration Operations

Human exploration of space will involve remote autonomous crew and systems in long missions. Data to earth will be delayed and limited. Earth control centers will not receive continuous real-time telemetry data, and there will be communication round trips of up to one hour. There will be reduced human monitoring on the planet and earth. When crews are present on the planet, they will be occupied with other activities, and system management will be a low priority task. Earth control centers will use multi-tasking "night shift" and on-call specialists. A new project at Johnson Space Center is developing software to support teamwork between distributed human and software agents in future interplanetary work environments. The Engineering and Mission Operations Directorates at Johnson Space Center (JSC) are combining laboratories and expertise to carry out this project, by establishing a testbed for hWl1an centered design, development and evaluation of intelligent autonomous and assistant systems. Intelligent autonomous systems for managing systems on planetary bases will commuicate their knowledge to support distributed multi-agent mixed-initiative operations. Intelligent assistant agents will respond to events by developing briefings and responses according to instructions from human agents on earth and in space.

Malin, Jane T.↗
NASA NTRS2003

Self-Supervised Dynamical Systems

Some progress has been made in a continuing effort to develop mathematical models of the behaviors of multi-agent systems known in biology, economics, and sociology (e.g., systems ranging from single or a few biomolecules to many interacting higher organisms). Living systems can be characterized by nonlinear evolution of probability distributions over different possible choices of the next steps in their motions. One of the main challenges in mathematical modeling of living systems is to distinguish between random walks of purely physical origin (for instance, Brownian motions) and those of biological origin. Following a line of reasoning from prior research, it has been assumed, in the present development, that a biological random walk can be represented by a nonlinear mathematical model that represents coupled mental and motor dynamics incorporating the psychological concept of reflection or self-image. The nonlinear dynamics impart the lifelike ability to behave in ways and to exhibit patterns that depart from thermodynamic equilibrium. Reflection or self-image has traditionally been recognized as a basic element of intelligence. The nonlinear mathematical models of the present development are denoted self-supervised dynamical systems. They include (1) equations of classical dynamics, including random components caused by uncertainties in initial conditions and by Langevin forces, coupled with (2) the corresponding Liouville or Fokker-Planck equations that describe the evolutions of probability densities that represent the uncertainties. The coupling is effected by fictitious information-based forces, denoted supervising forces, composed of probability densities and functionals thereof. The equations of classical mechanics represent motor dynamics that is, dynamics in the traditional sense, signifying Newton s equations of motion. The evolution of the probability densities represents mental dynamics or self-image. Then the interaction between the physical and metal aspects of a monad is implemented by feedback from mental to motor dynamics, as represented by the aforementioned fictitious forces. This feedback is what makes the evolution of probability densities nonlinear. The deviation from linear evolution can be characterized, in a sense, as an expression of free will. It has been demonstrated that probability densities can approach prescribed attractors while exhibiting such patterns as shock waves, solitons, and chaos in probability space. The concept of self-supervised dynamical systems has been considered for application to diverse phenomena, including information-based neural networks, cooperation, competition, deception, games, and control of chaos. In addition, a formal similarity between the mathematical structures of self-supervised dynamical systems and of quantum-mechanical systems has been investigated.

Zak, Michail↗
NASA NTRS2026

Hydrology Copilot: A Cloud-Native Ai System for Hydrological Data Analysis

The emergence of AI-driven Earth observation systems promises to broaden access to petabyte-scale geospatial data beyond domain specialists. However, translating this vision into operational scientific infrastructure requires addressing fundamental challenges in data virtualization, code transparency, and domain-specific reasoning. We present Hydrology Copilot, a cloud-native AI framework for natural-language-driven analysis of Earth observation data. To demonstrate operational capabilities at scale, we implement the system using NASA's North American Land Data Assimilation System version 3 (NLDAS-3), which provides surface meteorological forcing and land-surface model output across North and Central America at 1-km resolution, from which drought diagnostics are derived. The system integrates five core contributions: (1) scalable data virtualization using Kerchunk-based cloud optimized access, achieving a 1.5 to 4.6 times improvement in I/O latency across benchmark queries spanning regional single-day extractions (4.6 times speedup) to continental monthly aggregations (1.5 times speedup); (2) transparent code generation through Microsoft Azure AI Foundry agents that expose executable Python workflows for scientific verification; (3) persistent conversational memory enabling multi-turn analytical discourse across sessions; (4) intelligent query validation that enforces dataset boundaries and resolves ambiguous requests before execution; and (5) a multi-agent architecture coordinating query parsing, code generation, and visualization. We evaluate the system through drought-monitoring workflows, demonstrating reliable code generation, accurate results validated against reference computations and the operational U.S. Drought Monitor, and efficient operation across increasingly complex tasks. By bridging natural-language interfaces with rigorous hydrological analysis, Hydrology Copilot advances beyond proof-of-concept demonstrations to provide a deployable framework for operational Earth science applications.

Data virtualization↗
DOE OSTI2025

LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers

Liquid cooling is critical for thermal management in high-density data centers with the rising AI workloads. However, machine learning-based controllers are essential to unlock greater energy efficiency and reliability, promoting sustainability. We present LC-Opt, a Sustainable Liquid Cooling (LC) benchmark environment, for reinforcement learning (RL) control strategies in energy-efficient liquid cooling of high-performance computing (HPC) systems. Built on the baseline of a high-fidelity digital twin of Oak Ridge National Lab's Frontier Supercomputer cooling system, LC-Opt provides detailed Modelica-based end-to-end models spanning site-level cooling towers to data center cabinets and server blade groups. RL agents optimize critical thermal controls like liquid supply temperature, flow rate, and granular valve actuation at the IT cabinet level, as well as cooling tower (CT) setpoints through a Gymnasium interface, with dynamic changes in workloads. This environment creates a multi-objective real-time optimization challenge balancing local thermal regulation and global energy efficiency, and also supports additional components like a heat recovery unit (HRU). We benchmark centralized and decentralized multi-agent RL approaches, demonstrate policy distillation into decision and regression trees for interpretable control, and explore LLM-based methods that explain control actions in natural language through an agentic mesh architecture designed to foster user trust and simplify system management. LC-Opt democratizes access to detailed, customizable liquid cooling models, enabling the ML community, operators, and vendors to develop sustainable data center liquid cooling control solutions.

Naug, Avisek [Hewlett Packard Enterprise]↗
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 OSTI2025

The Cost of Scaling Up in Large-Format Additive Manufacturing

Additive manufacturing (AM) of large objects has, over the last decade, required the scaling of existing material extrusion processes. The current generation of large-scale printers are primarily gantry robots with high-throughput extrusion systems. With workspaces approaching 50 m 3 , these printers have pushed the boundaries of achievable print volume while allowing the utilization of low-cost feedstocks, such as cementitious materials and polymer pellets, like those used in injection molding. Continued workspace expansion requires an examination of the inherent trade-offs, which impact capital and operational costs. Here, in this work, the authors examine these trade-offs to determine fundamental scaling laws for existing system architectures, survey the state of the art for alternative system configurations, and pose recommendations for future system designers to continue the evolution of large-scale AM systems.

3D printing↗
DOE OSTI2025

Privacy-Preserving Average Consensus With Beaver Triple and Communication Obfuscation

A privacy-preserving average consensus algorithm is proposed that synergizes the Beaver triple in secret sharing theory and noise obfuscation. The algorithm safeguards the initial values of agents against passive adversaries in a multiagent system. It is proved that the proposed algorithm can concurrently ensure average consensus and privacy, while also reducing the online computation and communication overhead compared to encryption-based ones. In addition, it imposes a less stringent condition for privacy preservation compared to certain noise-obfuscation techniques.

Beaver triple↗