Simultaneous Policy and Discrete Communication Learning for Multi-Agent Cooperation
Not provided.
Robotics↗
SEARCH · Search NASA
Results for “multi-agent cooperation”
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.
PowerNet: Multi-agent Deep Reinforcement Learning for Scalable Powergrid Control
This paper develops an efficient multi-agent deep reinforcement learning algorithm for cooperative controls in powergrids. Specifically, we consider the decentralized inverter-based secondary voltage control problem in distributed generators (DGs), which is first formulated as a cooperative multi-agent reinforcement learning (MARL) problem. We then propose a novel on-policy MARL algorithm, PowerNet, in which each agent (DG) learns a control policy based on (sub-)global reward but local states and encoded communication messages from its neighbors. Motivated by the fact that a local control from one agent has limited impact on agents distant from it, we exploit a novel spatial discount factor to reduce the effect from remote agents, to expedite the training process and improve scalability. Furthermore, a differentiable, learning-based communication protocol is employed to foster the collaborations among neighboring agents. In addition, to mitigate the effects of system uncertainty and random noise introduced during on-policy learning, we utilize an action smoothing factor to stabilize the policy execution. To facilitate training and evaluation, we develop PGSim, an efficient, high-fidelity powergrid simulation platform. Here, experimental results in two microgrid setups show that the developed PowerNet outperforms the conventional model-based control method, as well as several state-of-the-art MARL algorithms. The decentralized learning scheme and high sample efficiency also make it viable to large-scale power grids.
24 POWER TRANSMISSION AND DISTRIBUTION↗
Optimization-based approaches to control of connected and automated vehicles: Principles, complexities, applications, challenges, and outlook
Safe and optimal motion control for connected and automated vehicles (CAVs) poses a fundamental optimization challenge at the intersection of system complexity, environmental uncertainty, and stringent real-time constraints. Existing surveys address this challenge in isolation – focusing either on specific control techniques or individual uncertainty sources – without providing a unified framework that characterizes the trade-offs among computational tractability, performance verifiability, and adaptive generalization across paradigms. This review addresses that gap by presenting a cohesive analytical framework concentrated on the decision-making and trajectory optimization layers of the CAV autonomy stack. We systematically analyze three major optimization paradigms – first-principles model-based optimization, data-driven methods, and hybrid synergistic architectures – evaluating each against four core complexity axes: problem formulation, constraint handling, optimality guarantees, and robustness. Key applications including platooning, trajectory planning, collision avoidance, and cooperative control are examined to reveal recurring methodological patterns and critical operational constraints that limit real-world performance. Our synthesis identifies verifiable hybrid architectures, incentive-aligned multi-agent cooperation, and hardware-algorithm co-design as the defining research frontiers, and distills a targeted agenda for developing CAV control systems that are simultaneously safe, computationally efficient, and deployable in the full complexity of real-world traffic environments.
Muzahid, Abu Jafar Md [University of Tennessee, Kn↗
Reinforcement Learning for Volt- Var Control: A Novel Two-stage Progressive Training Strategy
This paper develops a reinforcement learning (RL) approach to solve a cooperative, multi-agent Volt-Var Control (VVC) problem for high solar penetration distribution systems. The ingenuity of our RL method lies in a novel two-stage progressive training strategy that can effectively improve training speed and convergence of the machine learning algorithm. In Stage 1 (individual training), while holding all the other agents inactive, we separately train each agent to obtain its own optimal VVC actions in the action space: fconsume, generate, do-nothingg. In Stage 2 (cooperative training), all agents are trained again coordinatively to share VVC responsibility. Rewards and costs in our RL scheme include (i) a system-level reward (for taking an action), (ii) an agent-level reward (for doing-nothing), and (iii) an agent-level action cost function. This new framework allows rewards to be dynamically allocated to each agent based on their contribution while accounting for the trade-off between control effectiveness and action cost. The proposed methodology is tested and validated in a modified IEEE 123-bus system using realistic PV and load profiles. Simulation results confirm that the proposed approach is robust and computationally efficient; and it achieves desirable volt-var control performance under a wide range of operation conditions.
24 POWER TRANSMISSION AND DISTRIBUTION↗
Robust Decentralized Learning Using ADMM With Unreliable Agents
Many signal processing and machine learning problems can be formulated as consensus optimization problems which can be solved efficiently via a cooperative multi-agent system. However, the agents in the system can be unreliable due to a variety of reasons: noise, faults and attacks. Providing erroneous updates leads the optimization process in a wrong direction, and degrades the performance of distributed machine learning algorithms. This paper considers the problem of decentralized learning using ADMM in the presence of unreliable agents. First, we rigorously analyze the effect of erroneous updates (in ADMM learning iterations) on the convergence behavior of the multi-agent system. We show that the algorithm linearly converges to a neighborhood of the optimal solution under certain conditions and characterize the neighborhood size analytically. Next, we provide guidelines for network design to achieve a faster convergence to the neighborhood. Here, we also provide conditions on the erroneous updates for exact convergence to the optimal solution. Finally, to mitigate the influence of unreliable agents, we propose ROAD , a robust variant of ADMM, and show its resilience to unreliable agents with an exact convergence to the optimum.
97 MATHEMATICS AND COMPUTING↗
Incentivizing Cooperative Merging Control: Insights from Multi-Agent Deep Reinforcement Learning
Cooperative driving automation enables connected and automated vehicles (CAVs) to devise cooperative merging control, introducing great potentials to alleviate traffic congestion, reduce energy consumption, and enhance safety for highway on-ramp operations. Although numerous CAV cooperative merging algorithms have been developed to improve energy and traffic performance, the agreement-seeking among CAV users and their local benefits have been understudied. This can lead to rejections of cooperative merging plans and jeopardizing CAV performance, as a cooperation may entail certain CAVs to sacrifice their local benefits to achieve a system optimum. To address this issue, the study first leverages multi-agent deep reinforcement learning (MADRL) factoring both local reward and regional reward to demonstrate the discrepancies between CAV users’ local benefits and system optimum. Next, the existence of a correlated equilibrium is proved to characterize the convergence of MADRL training. This further facilitates the incorporation of incentives (computed based on reward discrepancies) to compensate for CAV users’ local benefits and facilitate system-optimal agreements in cooperative merging operations.
Zhou, Anye [ORNL] (ORCID:0000000301455579)↗
Neural correspondence to spectrum of environmental uncertainty in multiple-cue probability judgment system with time delay
Despite state-of-the-art technologies like artificial intelligence, human judgment is critically essential in cooperative systems, such as the multi-agent system (MAS), which collect information among agents based on multiple-cue judgment. Human agents can prevent impaired situational awareness of automated agents by confirming situations under environmental uncertainty. System error caused by uncertainty can result in an unreliable system environment, and this environment affects the human agent, resulting in non-optimal decision-making in MAS. Thus, it is necessary to know how human behavior is changed to capture system reliability under uncertainty. Another issue affecting MAS is time delay, which can delay agent information transfer, resulting in low performance and instability. However, it is difficult to find studies on the influence of time delay on human agents. This study is about understanding the human decision-making process under a specific system reliability environment by uncertainty with time delay. We used concepts of expected and unexpected uncertainty to implement reliability of the system usage environment with three types of time delay conditions: no time delay, regular time delay, and irregular time delay conditions. We used electroencephalogram (EEG) for human cognitive neural mechanisms in multiple-cue judgment systems to understand human decision-making. In the reliability of system usage environment, the unreliable system environment significantly creates less memory load by less utilization of system rules for decision-making. In terms of time delay, delayed information delivery does not significantly affect memory load for decision-making.
cognitive process↗
Minimal Energy Routing of a Leader and a Wingmate with Periodic Connectivity
We consider a route planning problem in which two unmanned vehicles are required to complete a set of tasks present at distinct locations, referred to as targets, with minimum energy consumption. The mission environment is hazardous, and to ensure a safe operation, the UVs are required to communicate with each other at every target they visit. The problem objective is to determine the allocation of the tasks to the UVs and plan tours for the UVs to visit the targets such that the weighted sum of the distances traveled by the UVs and the distances traveled by the communicating signals between them is minimized. We formulate this problem as an Integer program and show that naively solving the problem using commercially available off-the-shelf solvers is insufficient in determining scalable solutions efficiently. To address this computational challenge, we develop an approximation and a heuristic algorithm, and employ them to compute high-quality solutions to a special case of the problem where equal weights are assigned to the distances traveled by the vehicles and the communicating signals. For this special case, we show that the approximation algorithm has a fixed approximation ratio of 3.75. We also develop lower bounds to the optimal cost of the problem to evaluate the performance of these algorithms on large-scale instances. We demonstrate the performance of these algorithms on 500 randomly generated instances with the number of targets ranging from 6 to 100, and show that the algorithms provide high-quality solutions to the problem swiftly; the average computation time of the algorithmic solutions is within a fraction of a second for instances with at most 100 targets. Finally, we show that the approximation ratio has a variable ratio for the weighted case of the problem. Specifically, if ρ denotes the ratio of the weights assigned to the distances representing the communication and travel costs, the algorithm has an a posteriori ratio of $3 + \frac{3ρ}{4}$ when ρ ≥ 1, and $\frac{3}{ρ}$ + $\frac{3}{4}$ when ρ ≤ 1.
42 ENGINEERING↗
Scalable/Secure Cooperative Algorithms and Framework for Extremely-high Penetration Solar Integration (SolarExPert) (Final Technical Report)
This SolarExPert project has developed a Sustainable Grid Platform (SGP) with scalable architecture of distributed control and optimization. The SGP consists of the following major functions: 1) an advanced grid architecture with hierarchical and distributed communication and control, combined with the OpenFMB standard and implemented on the Multi-Agent OpenDSS (MA-OpenDSS) platform; 2) an online distributed stochastic optimal power flow; 3) an online distributed system state estimation algorithm; 4) the distributed Volt/VAR optimization and frequency control algorithms; 5) the distributed distribution system restoration strategy. The developed SGP together with advanced functions are tested in 1 million (1M)-node distribution system on the MA-OpenDSS platform. Furthermore, the models and algorithms are tested in 100,000-node system HiL simulation, and also in P-HiL implementation with 100 physical devices. The developed functions haven been validated and tested on the selected actual distribution feeder with the data collected from the field of Maui Meadows in Hawaii. The distributed PV hosting capacities with cooperative Volt/VAR and Volt/VAR/Watt control are estimated and compared to provide recommendations for customers and the utility company.
14 SOLAR ENERGY↗
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↗
Self-Aware Local Autonomous and Semi-Cooperative Control for Cross-Layered Resilience (SLAC3R)
The objective of this work is to develop and demonstrate novel, adaptive, lightweight algorithms that enable the decision-making agents in a large cyber-physical network to act both autonomously and in collaborative harmony to enforce assured resilience across spatiotemporal layers, even under unforeseen adversarial scenarios (e.g., high- impact-low-probability events). Towards this end, the proposed solution will serve as minimally invasive add-on layers that bridge the existing (faster, reactive) local myopic controls and (slower, predictive) centralized optimization. Importantly, the proposed algorithms will enable the multi-agent network to autonomously and collaboratively enforce resilient operation under no or limited communication environment typical of severe cyber- physical adversarial events. The expected outcome of this effort is a suite of prototype, open-source, software algorithms for safety-aware local autonomous and semi-cooperative control (SLAC3R), demonstrated on networked microgrids (via RD2C/Thrust-1 OPAL-RT testbed).
97 MATHEMATICS AND COMPUTING↗
Network-Level Traffic Signal Cooperation: A Higher-Order Conflict Graph Approach
Traffic signal control and cooperation are extremely important to alleviate traffic congestion in a large traffic network. This study develops a higher-order conflict graph approach for network-wide traffic signal control and cooperation. A conflict graph is applied to model the traffic signal configurations, which identifies the conflict and unconflicted movements for each intersection. In conflict graph, the node represents each movement. The weight of each node can be defined as traffic volume, queue length, fuel consumption, or any weighted combinations of these measurements. The calculation of the optimal green light duration and green light sequence (for different movements) is equivalent to sequentially finding the maximum weight independent set (MWIS) in the conflict graph. The conflict graph also provides a uniform and efficient way to connect traffic signal operations among nearby intersections spatially. Then, we introduced the concept of the k -th order neighborhood to model the degree of connectivity between each movement to the movements at upstream or downstream intersections. The weight of each node in the higher-order conflict graph not only represents its own congestion level, but also relates to the traffic conditions of nearby intersections. Through this approach, the cooperation of multiple intersections can be realized by incorporating their spatial connectivity into conflict graph and solving the MWIS problem. A simulation network is built in SUMO to test the effectiveness of the proposed method. Results suggested that the proposed model outperformed other state-of-the-art signal control methods. Also, the scheme maintains good performance under varying traffic demands.
42 ENGINEERING↗
Blockchain Enabled Intelligence of Federated Systems (BELIEFS): An attack-tolerant trustable distributed intelligence paradigm
In this article, a Blockchain Enabled Intelligence of Federated Systems (BELIEFS) is proposed to conduct cooperative control for the multi-regional large-scale power system with a multi-agents system (MAS). By establishing a two levels blockchain, each regional AI agent can simultaneously manage intra-regional controllers and cooperate with other AI agents. Under the consensus mechanism, the agents, which respectively conducted distributed deep reinforcement learning (DDRL) algorithm in multi-regions, can have the tolerant capability of malicious attacks in their training process. The demonstration of the proposed approach is within a multi-regional large-scale interconnected power system. Under the mode of "centralized dispatching and hierarchical management", this article aims to definite a mathematical model to deal with the control problem of the power systems. With the comparison experiments, the effectiveness and efficiency of our proposed method in the training process are verified. In addition, malicious attacks are set on the main chain and shard chains to verify the attack-tolerant capability. We expect that such approach and results can suggest a new paradigm of attack-tolerant trustable distributed AI deployment.
97 MATHEMATICS AND COMPUTING↗
A non-cooperative meta-modeling game for automated third-party calibrating, validating and falsifying constitutive laws with parallelized adversarial attacks
The evaluation of constitutive models, especially for high-risk and high-regret engineering applications, requires efficient and rigorous third-party calibration, validation and falsification. While there are numerous efforts to develop paradigms and standard procedures to validate models, difficulties may arise due to the sequential, manual, and often biased nature of the commonly adopted calibration and validation processes, thus slowing down data collections, hampering the progress towards discovering new physics, increasing expenses and possibly leading to misinterpretations of the credibility and application ranges of proposed models. This work attempts to introduce concepts from game theory and machine learning techniques to overcome many of these existing difficulties. Here, we introduce an automated meta-modeling game where two competing AI agents systematically generate experimental data to calibrate a given constitutive model and to explore its weakness such that the experiment design and model robustness can be improved through competitions. The two agents automatically search for the Nash equilibrium of the meta-modeling game in an adversarial reinforcement learning framework without human intervention. In particular, a protagonist agent seeks to find the more effective ways to generate data for model calibrations, while an adversary agent tries to find the most devastating test scenarios that expose the weaknesses of the constitutive model calibrated by the protagonist. By capturing all possible design options of the laboratory experiments into a single decision tree, we recast the design of experiments as a game of combinatorial moves that can be resolved through deep reinforcement learning by the two competing players. Our adversarial framework emulates idealized scientific collaborations and competitions among researchers to achieve a better understanding of the application range of the learned material laws and prevent misinterpretations caused by conventional AI-based third-party validation. Numerical examples are given to demonstrate the wide applicability of the proposed meta-modeling game with adversarial attacks on both human-crafted constitutive models and machine learning models.
97 MATHEMATICS AND COMPUTING↗