Multi-Agent Reinforcement Learning

Also known as MARL

Ask about this topic

Overview

Multi-agent reinforcement learning studies how multiple decision-makers learn when each agent’s actions affect both the environment and other agents, across cooperative, competitive, and mixed-motive settings. Common approaches include centralized training with decentralized execution, independent or shared actor-critic policies, value factorization such as QMIX, self-play and game-solving methods, and graph-based communication or hierarchical policies. Researchers test these methods in benchmarks such as SMAC, MPE, Overcooked, and multi-agent MuJoCo, and apply them to robotics, traffic, wireless networks, energy systems, and language-agent workflows. A central challenge is scaling coordination and credit assignment while keeping learning stable under non-stationarity and policies robust, safe, and fair with unfamiliar partners and conditions.

Latest papers

CardsList

373 papers47 papers in the last four weeks, up 81% on the four weeks before. 0.3% of all new papers.

Mar 12, 2026

A Robust and Efficient Multi-Agent Reinforcement Learning Framework for Traffic Signal Control

Reinforcement Learning (RL) in Traffic Signal Control (TSC) faces significant hurdles in real-world deployment due to limited generalization to dynamic traffic flow variations. Existing approaches often overfit static patterns and use action spaces incompatible with driver expectations. This paper proposes a robust Multi-Agent Reinforcement Learning (MARL) framework validated in the Vissim traffic simulator. The framework integrates three mechanisms: (1) Turning Ratio Randomization, a training strategy that exposes agents to dynamic turning probabilities to enhance robustness against unseen scenarios; (2) a stability-oriented Exponential Phase Duration Adjustment action space, which balances responsiveness and precision through cyclical, exponential phase adjustments; and (3) a Neighbor-Based Observation scheme utilizing the MAPPO algorithm with Centralized Training with Decentralized Execution (CTDE). By leveraging centralized updates, this approach approximates the efficacy of global observations while maintaining scalable local communication. Experimental results demonstrate that our framework outperforms standard RL baselines, reducing average waiting time by over 10%. The proposed model exhibits superior generalization in unseen traffic scenarios and maintains high control stability, offering a practical solution for adaptive signal control.

Sheng-You Huang, Hsiao-Chuan Chang, Yen-Chi Chen +6

National Yang Ming Chiao Tung University · Academia Sinica · Kochi University of Technology +1

Centralized Training with Decentralized ExecutionReinforcement LearningMulti-Agent Reinforcement LearningRobust RL
AskPDF
Mar 12, 2026

Exploiting Expertise of Non-Expert and Diverse Agents in Social Bandit Learning: A Free Energy Approach

Personalized AI-based services involve a population of individual reinforcement learning agents. However, most reinforcement learning algorithms focus on harnessing individual learning and fail to leverage the social learning capabilities commonly exhibited by humans and animals. Social learning integrates individual experience with observing others' behavior, presenting opportunities for improved learning outcomes. In this study, we focus on a social bandit learning scenario where a social agent observes other agents' actions without knowledge of their rewards. The agents independently pursue their own policy without explicit motivation to teach each other. We propose a free energy-based social bandit learning algorithm over the policy space, where the social agent evaluates others' expertise levels without resorting to any oracle or social norms. Accordingly, the social agent integrates its direct experiences in the environment and others' estimated policies. The theoretical convergence of our algorithm to the optimal policy is proven. Empirical evaluations validate the superiority of our social learning method over alternative approaches in various scenarios. Our algorithm strategically identifies the relevant agents, even in the presence of random or suboptimal agents, and skillfully exploits their behavioral information. In addition to societies including expert agents, in the presence of relevant but non-expert agents, our algorithm significantly enhances individual learning performance, where most related methods fail. Importantly, it also maintains logarithmic regret.

Erfan Mirzaei, Seyed Pooya Shariatpanahi, Alireza Tavakoli +2

The authors are with the Cognitive Systems Lab., School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran.

Multi-Armed BanditsMulti-Agent Reinforcement Learning
AskPDF
Mar 12, 2026

Multi-Agent Reinforcement Learning for UAV-Based Chemical Plume Source Localization

Undocumented orphaned wells pose significant health and environmental risks to nearby communities by releasing toxic gases and contaminating water sources, with methane emissions being a primary concern. Traditional survey methods such as magnetometry often fail to detect older wells effectively. In contrast, aerial in-situ sensing using unmanned aerial vehicles (UAVs) offers a promising alternative for methane emission detection and source localization. This study presents a robust and efficient framework based on a multi-agent deep reinforcement learning (MARL) algorithm for the chemical plume source localization (CPSL) problem. The proposed approach leverages virtual anchor nodes to coordinate UAV navigation, enabling collaborative sensing of gas concentrations and wind velocities through onboard and shared measurements. Source identification is achieved by analyzing the historical trajectory of anchor node placements within the plume. Comparative evaluations against the fluxotaxis method demonstrate that the MARL framework achieves superior performance in both localization accuracy and operational efficiency.

Zhirun Li, Derek Hollenbeck, Ruikun Wu +4

Department of Electrical and Computer Engineering, University of New Mexico, Albuquerque, NM 87131 USA · Department of Mechanical Engineering, University of California, Merced, CA 95343 USA · Department of Electrical Engineering, Colorado School of Mines, Golden, CO 80401 USA +3

Multi-Agent Reinforcement LearningUAV Navigation
AskPDF
Mar 11, 2026

Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning

Humanoid robotics has strong potential to transform daily service and caregiving applications. Although recent advances in general motion tracking within physics engines (GMT) have enabled virtual characters and humanoid robots to reproduce a broad range of human motions, these behaviors are primarily limited to contact-less social interactions or isolated movements. Assistive scenarios, by contrast, require continuous awareness of a human partner and rapid adaptation to their evolving posture and dynamics. In this paper, we formulate the imitation of closely interacting, force-exchanging human-human motion sequences as a multi-agent reinforcement learning problem. We jointly train partner-aware policies for both the supporter (assistant) agent and the recipient agent in a physics simulator to track assistive motion references. To make this problem tractable, we introduce a partner policies initialization scheme that transfers priors from single-human motion-tracking controllers, greatly improving exploration. We further propose dynamic reference retargeting and contact-promoting reward, which adapt the assistant's reference motion to the recipient's real-time pose and encourage physically meaningful support. We show that AssistMimic is the first method capable of successfully tracking assistive interaction motions on established benchmarks, demonstrating the benefits of a multi-agent RL formulation for physically grounded and socially aware humanoid control.

Yuto Shibata, Kashu Yamazaki, Lalit Jayanti +3

Carnegie Mellon University · Keio AI Research Center · Keio University

Humanoid Robot ControlAssistive RoboticsRobot Imitation LearningMulti-Agent Reinforcement Learning
AskPDF
Mar 11, 2026

UAV-MARL: Multi-Agent Reinforcement Learning for Time-Critical and Dynamic Medical Supply Delivery

Unmanned aerial vehicles (UAVs) are increasingly used to support time-critical medical supply delivery, providing rapid and flexible logistics during emergencies and resource shortages. However, effective deployment of UAV fleets requires coordination mechanisms capable of prioritizing medical requests, allocating limited aerial resources, and adapting delivery schedules under uncertain operational conditions. This paper presents a multi-agent reinforcement learning (MARL) framework for coordinating UAV fleets in stochastic medical delivery scenarios where requests vary in urgency, location, and delivery deadlines. The problem is formulated as a partially observable Markov decision process (POMDP) in which UAV agents maintain awareness of medical delivery demands while having limited visibility of other agents due to communication and localization constraints. The proposed framework employs Proximal Policy Optimization (PPO) as the primary learning algorithm and evaluates several variants, including asynchronous extensions, classical actor--critic methods, and architectural modifications to analyze scalability and performance trade-offs. The model is evaluated using real-world geographic data from selected clinics and hospitals extracted from the OpenStreetMap dataset. The framework provides a decision-support layer that prioritizes medical tasks, reallocates UAV resources in real time, and assists healthcare personnel in managing urgent logistics. Experimental results show that classical PPO achieves superior coordination performance compared to asynchronous and sequential learning strategies, highlighting the potential of reinforcement learning for adaptive and scalable UAV-assisted healthcare logistics.

Islam Guven, Mehmet Parlak

ICTEAM, Université catholique de Louvain Ottignies-Louvain-la-Neuve, Belgium

Multi-Agent CoordinationMulti-Agent Reinforcement LearningAerial RoboticsPartially Observable RLProximal Policy Optimization
AskPDF
Mar 11, 2026

COHORT: Hybrid RL for Collaborative Large DNN Inference on Multi-Robot Systems Under Real-Time Constraints

Large deep neural networks (DNNs), especially transformer-based and multimodal architectures, are computationally demanding and challenging to deploy on resource-constrained edge platforms like field robots. These challenges intensify in mission-critical scenarios (e.g., disaster response), where robots must collaborate under tight constraints on bandwidth, latency, and battery life, often without infrastructure or server support. To address these limitations, we present COHORT, a collaborative DNN inference and task-execution framework for multi-robot systems built on the Robotic Operating System (ROS). COHORT employs a hybrid offline-online reinforcement learning (RL) strategy to dynamically schedule and distribute DNN module execution across robots. Our key contributions are threefold: (a) Offline RL policy learning combined with Advantage-Weighted Regression (AWR), trained on auction-based task allocation data from heterogeneous DNN workloads across distributed robots, (b) Online policy adaptation via Multi-Agent PPO (MAPPO), initialized from the offline policy and fine-tuned in real time, and (c) comprehensive evaluation of COHORT on vision-language model (VLM) inference tasks such as CLIP and SAM, analyzing scalability with increasing robot/workload and robustness under . We benchmark COHORT against genetic algorithms and multiple RL baselines. Experimental results demonstrate that COHORT reduces battery consumption by 15.4% and increases GPU utilization by 51.67%, while satisfying frame-rate and deadline constraints 2.55 times of the time.

Mohammad Saeid Anwar, Anuradha Ravi, Indrajeet Ghosh +3

University of Maryland Baltimore County · DEVCOM Army Research Laboratory

Efficient Neural Network InferenceMulti-Robot Task AllocationMulti-Agent Reinforcement Learning
AskPDF
Mar 11, 2026

Quantum entanglement provides a competitive advantage in adversarial games

Whether uniquely quantum resources confer advantages in fully classical, competitive environments remains an open question. Competitive zero-sum reinforcement learning is particularly challenging, as success requires modelling dynamic interactions between opposing agents rather than static state-action mappings. Here, we conduct a controlled study isolating the role of quantum entanglement in a quantum-classical hybrid agent trained on Pong, a competitive Markov game. An 8-qubit parameterised quantum circuit serves as a feature extractor within a proximal policy optimisation framework, allowing direct comparison between separable circuits and architectures incorporating fixed (CZ) or trainable (IsingZZ) entangling gates. Entangled circuits consistently outperform separable counterparts with comparable parameter counts and, in low-capacity regimes, match or exceed classical multilayer perceptron baselines. Representation similarity analysis further shows that entangled circuits learn structurally distinct features, consistent with improved modelling of interacting state variables. These findings establish entanglement as a function resource for representation learning in competitive reinforcement learning.

Peiyong Wang, Kieran Hymas, James Quach

Technology, CSIRO Clayton, Research Way, Clayton, VIC 3168, Australia.

Quantum RLQuantum Machine LearningRepresentation Learning for RLQuantum Neural NetworksMulti-Agent Reinforcement LearningHybrid Quantum-Classical ML
AskPDF
Mar 10, 2026

Octopus-inspired Distributed Control for Soft Robotic Arms: A Graph Neural Network-Based Attention Policy with Environmental Interaction

This paper proposes SoftGM, an octopus-inspired distributed control architecture for segmented soft robotic arms that learn to reach targets in contact-rich environments using online obstacle discovery without assuming full obstacle geometry at the start of each episode. SoftGM formulates each arm section as a cooperative agent and represents the arm-environment interaction as a graph. SoftGM uses a two-stage graph attention message passing scheme following a Centralised Training Decentralised Execution (CTDE) paradigm with a centralised critic and decentralised actor. We evaluate SoftGM in a Cosserat-rod simulator (PyElastica) across three tasks that increase the complexity of the environment: obstacle-free, structured obstacles, and a wall-with-hole scenario. Compared with six widely used MARL baselines (IDDPG, IPPO, ISAC, MADDPG, MAPPO, MASAC) under identical information content and training conditions, SoftGM matches strong CTDE methods in simpler settings and achieves the best performance in the wall-with-hole task. Robustness tests with observation noise, single-section actuation failure, and transient disturbances show that SoftGM maintains comparable performance under non-ideal simulated conditions while keeping control effort bounded, suggesting that selective contact-relevant information routing improves resilience in the tested settings.

Linxin Hou, Qirui Wu, Zhihang Qin +2

Department of Electrical and Computer Engineering, National University of Singapore, Singapore · Department of Computer Science, National University of Singapore, Singapore · Department of Mechanical Engineering, National University of Singapore, Singapore +2

Continuum Robot ControlDecentralized MARLSoft RoboticsMulti-Agent Reinforcement Learning
AskPDF
Mar 10, 2026

Code-Space Response Oracles: Generating Interpretable Multi-Agent Policies with Large Language Models

Recent advances in multi-agent reinforcement learning, particularly Policy-Space Response Oracles (PSRO), have enabled the computation of approximate game-theoretic equilibria in increasingly complex domains. However, these methods rely on deep reinforcement learning oracles that produce `black-box' neural network policies, making them difficult to interpret, trust or debug. We introduce Code-Space Response Oracles (CSRO), a novel framework that addresses this challenge by replacing RL oracles with Large Language Models (LLMs). CSRO reframes the best response computation as a code generation task, prompting an LLM to generate policies directly as human-readable code. This approach not only yields inherently interpretable policies but also leverages the LLM's pretrained knowledge to discover complex, human-like strategies. We explore multiple ways to construct and enhance an LLM-based oracle: zero-shot prompting, iterative refinement and AlphaEvolve, a distributed LLM-based evolutionary system. We demonstrate that CSRO achieves performance competitive with baselines while producing a diverse set of explainable policies. Our work presents a new perspective on multi-agent learning, shifting the focus from optimizing opaque policy parameters to synthesizing interpretable algorithmic behavior.

Daniel Hennes, Zun Li, John Schultz +1

Google DeepMind

Multi-Agent Reinforcement LearningInterpretability in RLLLM-Guided RL
AskPDF
Mar 10, 2026

Strategically Robust Multi-Agent Reinforcement Learning with Linear Function Approximation

Provably efficient and robust equilibrium computation in general-sum Markov games remains a core challenge in multi-agent reinforcement learning. Nash equilibrium is computationally intractable in general and brittle due to equilibrium multiplicity and sensitivity to approximation error. We study Risk-Sensitive Quantal Response Equilibrium (RQRE), which yields a unique, smooth solution under bounded rationality and risk sensitivity. We propose RQRE-OVI, an optimistic value iteration algorithm for computing RQRE with linear function approximation in large or continuous state spaces. Through finite-sample regret analysis, we establish convergence and explicitly characterize how sample complexity scales with rationality and risk-sensitivity parameters. The regret bounds reveal a quantitative tradeoff: increasing rationality tightens regret, while risk sensitivity induces regularization that enhances stability and robustness. This exposes a Pareto frontier between expected performance and robustness, with Nash recovered in the limit of perfect rationality and risk neutrality. We further show that the RQRE policy map is Lipschitz continuous in estimated payoffs, unlike Nash, and RQRE admits a distributionally robust optimization interpretation. Empirically, we demonstrate that RQRE-OVI achieves competitive performance under self-play while producing substantially more robust behavior under cross-play compared to Nash-based approaches. These results suggest RQRE-OVI offers a principled, scalable, and tunable path for equilibrium learning with improved robustness and generalization.

Jake Gonzales, Max Horwitz, Eric Mazumdar +1

Department of Electrical & Computer Engineering, University of Washington · Computing & Mathematical Sciences, California Institute of Technology

Multi-Agent Reinforcement LearningGame-Theoretic RLGame TheoryRisk-Sensitive RL
AskPDF
Mar 9, 2026

Less is More: Robust Zero-Communication 3D Pursuit-Evasion via Representational Parsimony

Asymmetric 3D pursuit-evasion in cluttered voxel environments is difficult under communication latency, partial observability, and nonholonomic maneuver limits. While many MARL methods rely on richer inter-agent coupling or centralized signals, these dependencies can become fragility sources when communication is delayed or noisy. Building on an inherited path-guided decentralized pursuit scaffold, we study a robustness-oriented question: can representational parsimony improve communication-free coordination? We instantiate this principle with (i) a parsimonious actor observation interface that removes team-coupled channels (83-D to 50-D), and (ii) Contribution-Gated Credit Assignment (CGCA), a locality-aware credit structure for communication-denied cooperation. In Stage-5 evaluation (4 pursuers vs. 1 evader), our configuration reaches 0.753 +/- 0.091 success and 0.223 +/- 0.066 collision, outperforming the 83-D FULL OBS counterpart (0.721 +/- 0.071, 0.253 +/- 0.089). It further shows graceful degradation under speed/yaw/noise/delay stress tests and resilient zero-shot transfer on urban-canyon maps (about 61% success at density 0.24). These results support a practical paradigm shift: explicitly severing redundant cross-agent channels can suppress compounding error cascades and improve robustness in latency-prone deployment.

Jialin Ying, Zhihao Li, Zicheng Dong +2

Department of Automation, Central South University, Changsha, China

Multi-Agent SystemsMulti-Agent CoordinationDecentralized MARLMulti-Agent Reinforcement LearningMulti-Agent Communication
AskPDF
Mar 7, 2026

NePPO: Near-Potential Policy Optimization for General-Sum Multi-Agent Reinforcement Learning

Multi-agent reinforcement learning (MARL) is increasingly used to design learning-enabled agents that interact in shared environments. However, training MARL algorithms in general-sum games remains challenging: learning dynamics can become unstable, and convergence guarantees typically hold only in restricted settings such as two-player zero-sum or fully cooperative games. Moreover, when agents have heterogeneous and potentially conflicting preferences, it is unclear what system-level objective should guide learning. In this paper, we propose a new MARL pipeline called Near-Potential Policy Optimization (NePPO) for computing approximate Nash equilibria in mixed cooperative--competitive environments. The core idea is to learn a player-independent potential function such that the Nash equilibrium of a cooperative game with this potential as the common utility approximates a Nash equilibrium of the original game. To this end, we introduce a novel MARL objective such that minimizing this objective yields the best possible potential function candidate and consequently an approximate Nash equilibrium of the original game. We develop an algorithmic pipeline that minimizes this objective using zeroth-order gradient descent and returns an approximate Nash equilibrium policy. We empirically show the superior performance of this approach compared to popular baselines such as IPPO and MAPPO.

Addison Kalanther, Sanika Bharvirkar, Shankar Sastry +1

Electrical Engineering and Computer Sciences, UC Berkeley · Electrical and Computer Engineering, Data Science & Artificial Intelligence Institute, Johns Hopkins University

Multi-Agent Reinforcement LearningGame-Theoretic RLNash Equilibrium ComputationPotential Games
AskPDF
Mar 6, 2026

The Trace Is the State: Exact Credit Assignment for LLM Agent Teams

Credit assignment for a team of LLM agents, what each message was worth, has mostly been treated as prediction: a learned critic, a trajectory-level score, or an agent ablation stands in for the counterfactual that defines credit, which is rarely run. Teams that communicate through a shared context are different: when everything a downstream agent reads is written into the trace, the trace is the state, and that counterfactual can be executed. A credit signal can then be judged as any estimator is: by bias, variance, and agreement with an independent reference. C3, credit assignment by counterfactual continuation, substitutes one message at a decision point and continues the run to the terminal reward, so its credit is unbiased, exact up to Monte Carlo error. Given the sampled alternatives, that error's variance follows a derived law with no term for the number of agents, and the observed noise follows the law on 6 workflows of 2 to 10 decision points. On the 2-agent chain, from 4 continuations, C3 ranks alternatives at 0.69 rank correlation against a 16-continuation reference, near the 0.73 at which 2 such references agree; a critic trained on the same rollouts reaches 0.29. Used as the advantage in training a 2-agent team, C3 beats MAGRPO, the stronger baseline in our comparison, and spends 37% fewer training tokens than MAPPO, since only the messages downstream of a decision point are regenerated. When the trace is the state, credit need not be predicted; it can be exact.

Yanjun Chen, Yirong Sun, Hanlin Wang +5

Eastern Institute of Technology · The Hong Kong Polytechnic University · Harbin Institute of Technology

Credit AssignmentCounterfactual Credit AssignmentLLM Agent TrainingMulti-Agent LLM SystemsMulti-Agent Reinforcement Learning
AskPDF
Mar 6, 2026

Reinforcing the World's Edge: A Continual Learning Problem in the Multi-Agent-World Boundary

Ordinary decentralized multi-agent reinforcement learning presents each focal agent with a continual learning problem: peer updates change its induced rewards and dynamics even when the joint Markov game is stationary. We connect the lifetime of success-conditioned reusable structure to peer learning and policy reuse. An invariant core represents maximal abstract patterns shared by a high fraction of successful trajectories; survival refers to a fixed pattern's coverage, not an unchanged maximal frontier. An established sharp conditioning bound limits coverage loss to εp0\frac{\varepsilon}{p_0}, where ε\varepsilon is trajectory-law drift, p0p_0 is reference success mass, and drift is smaller than the initial compatible-success mass. Combining this bound with peer-policy movement certifies Ω(1η)Ω(\frac{1}η) survival under bounded peer updates of size ηη and positive coverage margin. An effective-conflict condition yields a matching Θ(1η)Θ(\frac{1}η) first-exit law and holds in an analytic exact-policy-gradient class. With success-mass and performance calibration, structural survival also yields policy-value and finite-library transfer guarantees. An exactly solvable corridor tests the structural predictions. Two registered 64-stream studies in continual control and cue-MNIST show that coverage erosion predicts impending failure and enables near-oracle intervention. An exploratory reanalysis of eight learned-partner Level-Based Foraging pairings suggests the same erosion--failure link under peer learning.

Dane Malenfant

School of Computer Science McGill University Mila - The Québec AI Institute

Non-Stationary RLDecentralized MARLPolicy LearningMulti-Agent Reinforcement LearningContinual RL
AskPDF
Mar 6, 2026

Multi-Agent Reinforcement Learning with Submodular Reward

In this paper, we study cooperative multi-agent reinforcement learning (MARL) where the joint reward exhibits submodularity, which is a natural property capturing diminishing marginal returns when adding agents to a team. Unlike standard MARL with additive rewards, submodular rewards model realistic scenarios where agent contributions overlap (e.g., multi-drone surveillance, collaborative exploration). We provide the first formal framework for this setting and develop algorithms with provable guarantees on sample efficiency and regret bound. For known dynamics, our greedy policy optimization achieves a 1/21/2-approximation with polynomial complexity in the number of agents KK, overcoming the exponential curse of dimensionality inherent in joint policy optimization. For unknown dynamics, we propose a UCB-based learning algorithm achieving a 1/21/2-regret of O(H2KSAT)O(H^2KS\sqrt{AT}) over TT episodes.

Wenjing Chen, Chengyuan Qian, Shuo Xing +2

Department of Computer Science and Engineering, Texas A&M University

Cooperative MARLMulti-Agent Reinforcement LearningSubmodular Optimization
AskPDF
Mar 5, 2026

Competitive Multi-Operator Reinforcement Learning for Joint Pricing and Fleet Rebalancing in AMoD Systems

Autonomous Mobility-on-Demand (AMoD) systems promise to revolutionize urban transportation by providing affordable on-demand services to meet growing travel demand. However, realistic AMoD markets will be competitive, with multiple operators competing for passengers through strategic pricing and fleet deployment. While reinforcement learning has shown promise in optimizing single-operator AMoD control, existing work fails to capture competitive market dynamics. We investigate the impact of competition on policy learning by introducing a multi-operator reinforcement learning framework where two operators simultaneously learn pricing and fleet rebalancing policies. By integrating discrete choice theory, we enable passenger allocation and demand competition to emerge endogenously from utility-maximizing decisions. Experiments using real-world data from multiple cities demonstrate that competition fundamentally alters learned behaviors, leading to lower prices and distinct fleet positioning patterns compared to monopolistic settings. Notably, we demonstrate that learning-based approaches are robust to the additional stochasticity of competition, with competitive agents successfully converging to effective policies while accounting for partially unobserved competitor strategies.

Emil Kragh Toft, Carolin Schmidt, Daniele Gammelli +1

Technical University of Denmark, Denmark · Technical University of Munich, Germany · Stanford University, USA

Dynamic PricingMulti-Agent Reinforcement LearningSequential MARL
AskPDF
Mar 5, 2026

SCoUT: Scalable Communication via Utility-Guided Temporal Grouping in Multi-Agent Reinforcement Learning

Communication can improve coordination in partially observed multi-agent reinforcement learning (MARL), but learning when and who to communicate with requires choosing among many possible sender-recipient pairs, and the effect of any single message on future reward is hard to isolate. We introduce SCoUT (Scalable Communication via Utility-guided Temporal grouping), which addresses both these challenges via temporal and agent abstraction within traditional MARL. During training, SCoUT resamples soft agent groups every KK environment steps (macro-steps) via Gumbel-Softmax; these groups are latent clusters that induce an affinity used as a differentiable prior over recipients. Using the same assignments, a group-aware critic predicts values for each agent group and maps them to per-agent baselines through the same soft assignments, reducing critic complexity and variance. Each agent is trained with a three-headed policy: environment action, send decision, and recipient selection. To obtain precise communication learning signals, we derive counterfactual communication advantages by analytically removing each sender's contribution from the recipient's aggregated messages. This counterfactual computation enables precise credit assignment for both send and recipient-selection decisions. At execution time, all centralized training components are discarded and only the per-agent policy is run, preserving decentralized execution. Project website, videos and code: \hyperlink{https://scout-comm.github.io/}{https://scout-comm.github.io/}

Manav Vora, Gokul Puthumanaillam, Hiroyasu Tsukamoto +1

University of Illinois Urbana-Champaign

Multi-Agent CommunicationMulti-Agent Reinforcement LearningCooperative MARLPartially Observable RL
AskPDF
Mar 4, 2026

MAGE: Meta-Reinforcement Learning for Language Agents toward Strategic Exploration and Exploitation

Large Language Model (LLM) agents have demonstrated remarkable proficiency in learned tasks, yet they often struggle to adapt to non-stationary environments with feedback. While In-Context Learning and external memory offer some flexibility, they fail to internalize the adaptive ability required for long-term improvement. Meta-Reinforcement Learning (meta-RL) provides an alternative by embedding the learning process directly within the model. However, existing meta-RL approaches for LLMs focus primarily on exploration in single-agent settings, neglecting the strategic exploitation necessary for multi-agent environments. We propose MAGE, a meta-RL framework that empowers LLM agents for strategic exploration and exploitation. MAGE utilizes a multi-episode training regime where interaction histories and reflections are integrated into the context window. By using the final episode reward as the objective, MAGE incentivizes the agent to refine its strategy based on past experiences. We further combine population-based training with an agent-specific advantage normalization technique to enrich agent diversity and ensure stable learning. Experiment results show that MAGE outperforms existing baselines in both exploration and exploitation tasks. Furthermore, MAGE exhibits strong generalization to unseen opponents, suggesting it has internalized the ability for strategic exploration and exploitation. Code is available at https://github.com/Lu-Yang666/MAGE.

Lu Yang, Zelai Xu, Minyang Xie +4

Tsinghua University

RL for LLM AgentsMeta-Reinforcement LearningExploration-Exploitation TradeoffMulti-Agent Reinforcement Learning
AskPDF
Mar 3, 2026

SPARC: Spatial-Aware Path Planning via Attentive Agent Communication

Efficient communication is critical for decentralized Multi-Robot Path Planning (MRPP), yet existing learned communication methods treat all neighboring robots equally regardless of their spatial proximity, leading to diluted attention in congested regions where coordination matters most. We propose Relation enhanced Multi Head Attention (RMHA), a communication mechanism that explicitly embeds pairwise Manhattan distances into the attention weight computation, enabling each robot to dynamically prioritize messages from spatially relevant neighbors. Combined with a distance-constrained attention mask and GRU gated message fusion, RMHA integrates seamlessly with MAPPO for stable end-to-end training. In zero-shot generalization from 8 training robots to 128 test robots on 40x40 grids, RMHA achieves approximately 75 percent success rate at 30 percent obstacle density outperforming the best baseline by over 25 percentage points. Ablation studies confirm that distance-relation encoding is the key contributor to success rate improvement in high-density environments. Index Terms-Multi-robot path planning, graph attention mechanism, multi-head attention, communication optimization, cooperative decision-making

Sayang Mu, Xiangyu Wu, Bo An

Nanyang Technological University Singapore

Multi-Robot Motion PlanningDecentralized Multi-Agent Motion PlanningMulti-Agent Path FindingMulti-Agent CommunicationMulti-Agent Reinforcement Learning
AskPDF
Mar 3, 2026

Generalized Per-Agent Advantage Estimation for Multi-Agent Policy Optimization

In this paper, we propose a novel framework for multi-agent reinforcement learning that enhances sample efficiency and coordination through accurate per-agent advantage estimation. The core of our approach is Generalized Per-Agent Advantage Estimator (GPAE), which employs a per-agent value iteration operator to compute precise per-agent advantages. This operator enables stable off-policy learning by indirectly estimating values via action probabilities, eliminating the need for direct Q-function estimation. To further refine estimation, we introduce a double-truncated importance sampling ratio scheme. This scheme improves credit assignment for off-policy trajectories by balancing sensitivity to the agent's own policy changes with robustness to non-stationarity from other agents. Experiments on benchmarks demonstrate that our approach outperforms existing approaches, excelling in coordination and sample efficiency for complex scenarios.

Seongmin Kim, Giseung Park, Woojun Kim +3

KAIST Daejeon, Korea · University of Toronto Toronto, Ontario, Canada · Carnegie Mellon University Pittsburgh, Pennsylvania, USA +1

Multi-Agent Reinforcement LearningSample-Efficient RLMulti-Agent Coordination
AskPDF
Mar 2, 2026

Personalized Multi-Agent Average Reward TD-Learning via Joint Linear Approximation

We study personalized multi-agent average reward TD learning, in which a collection of agents interacts with different environments and jointly learns their respective value functions. We focus on the setting where there exists a shared linear representation, and the agents' optimal weights collectively lie in an unknown linear subspace. Inspired by the recent success of personalized federated learning (PFL), we study the convergence of cooperative single-timescale TD learning in which agents iteratively estimate the common subspace and local heads. We showed that this decomposition can filter out conflicting signals, effectively mitigating the negative impacts of ``misaligned'' signals, and achieving linear speedup. The main technical challenges lie in the heterogeneity, the Markovian sampling, and their intricate interplay in shaping error evolutions. Specifically, not only are the error dynamics of multiple variables closely interconnected, but there is also no direct contraction for the principal angle distance between the optimal subspace and the estimated subspace. We hope our analytical techniques can be useful to inspire research on deeper exploration into leveraging common structures. Experiments are provided to show the benefits of learning via a shared structure to the more general control problem.

Leo Muxing Wang, Pengkun Yang, Lili Su

Northeastern University · Tsinghua University

Temporal-Difference LearningMulti-Agent Reinforcement LearningCooperative MARLAverage-Reward RLLinear Function Approximation
AskPDF
Mar 1, 2026

Epistemic Gain, Aleatoric Cost: Uncertainty Decomposition in Multi-Agent Debate for Math Reasoning

Multi-Agent Debate (MAD) has shown promise in improving reasoning and reducing hallucinations, yet it remains unclear how information exchange shapes individual reasoning behavior. Empirically, MAD exhibits paradoxical phenomena, including rising accuracy with increasing token entropy and marked differences between homogeneous and heterogeneous agent combinations. In this paper, we introduce a Bayesian uncertainty analysis framework for MAD, which decomposes answer-level predictive uncertainty into epistemic uncertainty and aleatoric uncertainty, corresponding to the potential gain and cost of debate. Across multiple agent configurations, we find that effective debate depends on achieving high epistemic gain under controlled aleatoric cost. Building on this insight, we design an uncertainty-guided multi-agent reinforcement learning algorithm that encourages lower aleatoric cost and more effective epistemic information utilization. Experiments show that our approach simultaneously enhances each agent's accuracy and promotes a more productive debate process, providing an operational Bayesian perspective for understanding and improving MAD.

Dan Qiao, Binbin Chen, Fengyu Cai +7

School of Data Science, The Chinese University of Hong Kong, Shenzhen, China · ByteDance, Beijing, China · Technical University of Darmstadt, Darmstadt, Germany +2

Multi-Agent DebateEpistemic UncertaintyAleatoric UncertaintyMulti-Agent Reinforcement Learning
AskPDF
Feb 28, 2026

MO-MIX: Multi-Objective Multi-Agent Cooperative Decision-Making With Deep Reinforcement Learning

Deep reinforcement learning (RL) has been applied extensively to solve complex decision-making problems. In many real-world scenarios, tasks often have several conflicting objectives and may require multiple agents to cooperate, which are the multi-objective multi-agent decision-making problems. However, only few works have been conducted on this intersection. Existing approaches are limited to separate fields and can only handle multi-agent decision-making with a single objective, or multi-objective decision-making with a single agent. In this paper, we propose MO-MIX to solve the multi-objective multi-agent reinforcement learning (MOMARL) problem. Our approach is based on the centralized training with decentralized execution (CTDE) framework. A weight vector representing preference over the objectives is fed into the decentralized agent network as a condition for local action-value function estimation, while a mixing network with parallel architecture is used to estimate the joint action-value function. In addition, an exploration guide approach is applied to improve the uniformity of the final non-dominated solutions. Experiments demonstrate that the proposed method can effectively solve the multi-objective multi-agent cooperative decision-making problem and generate an approximation of the Pareto set. Our approach not only significantly outperforms the baseline method in all four kinds of evaluation metrics, but also requires less computational cost.

Tianmeng Hu, Biao Luo, Chunhua Yang +1

School of Automation, Central South University, Changsha, 410012, China. · Texas A&M University at Qatar, Doha, 23874, Qatar.

Multi-Agent Reinforcement LearningMulti-Objective Reinforcement LearningCooperative MARL
AskPDF
Feb 28, 2026

Multi-Agent Reinforcement Learning for Dynamic Pricing: Balancing Profitability,Stability and Fairness

Dynamic pricing in competitive retail markets requires strategies that adapt to fluctuating demand and competitor behavior. In this work, we present a systematic empirical evaluation of multi-agent reinforcement learning (MARL) approaches-specifically MAPPO and MADDPG-for dynamic price optimization under competition. Using a simulated marketplace environment derived from real-world retail data, we benchmark these algorithms against an Independent DDPG (IDDPG) baseline, a widely used independent learner in MARL literature. We evaluate profit performance, stability across random seeds, fairness, and training efficiency. Our results show that MAPPO consistently achieves the highest average returns with low variance, offering a stable and reproducible approach for competitive price optimization, while MADDPG achieves slightly lower profit but the fairest profit distribution among agents. These findings demonstrate that MARL methods-particularly MAPPO-provide a scalable and stable alternative to independent learning approaches for dynamic retail pricing.

Krishna Kumar Neelakanta Pillai Santha Kumari Amma

Dynamic PricingReinforcement LearningMulti-Agent Reinforcement Learning
AskPDF
Feb 27, 2026

Conservative Equilibrium Discovery in Offline Game-Theoretic Multiagent Reinforcement Learning

Offline learning of strategies takes data efficiency to its extreme by restricting algorithms to a fixed dataset of state-action trajectories. We consider the problem in a mixed-motive multiagent setting, where the goal is to solve a game under the offline learning constraint. We first frame this problem in terms of selecting among candidate equilibria. Since datasets may inform only a small fraction of game dynamics, it is generally infeasible in offline game-solving to even verify a proposed solution is a true equilibrium. Therefore, we consider the relative probability of low regret (i.e., closeness to equilibrium) across candidates based on the information available. Specifically, we extend Policy Space Response Oracles (PSRO), an online game-solving approach, by quantifying game dynamics uncertainty and modifying the RL objective to skew towards solutions more likely to have low regret in the true game. We further propose a novel meta-strategy solver, tailored for the offline setting, to guide strategy exploration in PSRO. Our incorporation of Conservatism principles from Offline reinforcement learning approaches for strategy Exploration gives our approach its name: COffeE-PSRO. Experiments demonstrate COffeE-PSRO's ability to extract lower-regret solutions than state-of-the-art offline approaches and reveal relationships between algorithmic components empirical game fidelity, and overall performance.

Austin A. Nguyen, Michael P. Wellman

University of Michigan

Reinforcement LearningGame TheoryConservative RLOffline RLMulti-Agent Reinforcement LearningGame-Theoretic RL
AskPDF
Feb 27, 2026

TSC: Topology-Conditioned Stackelberg Coordination for Multi-Agent Reinforcement Learning in Interactive Driving

Safe and efficient autonomous driving in dense traffic is fundamentally a decentralized multi-agent coordination problem, where interactions at conflict points such as merging and weaving must be resolved reliably under partial observability. With only local and incomplete cues, interaction patterns can change rapidly, often causing unstable behaviors such as oscillatory yielding or unsafe commitments. Existing multi-agent reinforcement learning (MARL) approaches either adopt synchronous decision-making, which exacerbate non-stationarity, or depend on centralized sequencing mechanisms that scale poorly as traffic density increases. To address these limitations, we propose Topology-conditioned Stackelberg Coordination (TSC), a learning framework for decentralized interactive driving under communication-free execution, which extracts a time-varying directed priority graph from braid-inspired weaving relations between trajectories, thereby defining local leader-follower dependencies without constructing a global order of play. Conditioned on this graph, TSC endogenously factorizes dense interactions into graph-local Stackelberg subgames and, under centralized training and decentralized execution (CTDE), learns a sequential coordination policy that anticipates leaders via action prediction and trains followers through action-conditioned value learning to approximate local best responses, improving training stability and safety in dense traffic. Experiments across four dense traffic scenarios show that TSC achieves superior performance over representative MARL baselines across key metrics, most notably reducing collisions while maintaining competitive traffic efficiency and control smoothness.

Xiaotong Zhang, Gang Xiong, Yuanjing Wang +3

State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China · Department of Natural Sciences, University of Durham, Durham DH1 3LE, United Kingdom +4

Multi-Agent CoordinationDecentralized MARLRL for Autonomous DrivingMulti-Agent Reinforcement LearningSequential MARL
AskPDF
Feb 26, 2026

RLShield: Practical Multi-Agent RL for Financial Cyber Defense with Attack-Surface MDPs and Real-Time Response Orchestration

Financial systems run nonstop and must stay reliable even during cyber incidents. Modern attacks move across many services (apps, APIs, identity, payment rails), so defenders must make a sequence of actions under time pressure. Most security tools still use fixed rules or static playbooks, which can be slow to adapt when the attacker changes behavior. Reinforcement learning (RL) is a good fit for sequential decisions, but much of the RL-in-finance literature targets trading and does not model real cyber response limits such as action cost, service disruption, and defender coordination across many assets. This paper proposes RLShield, a practical multi-agent RL pipeline for financial cyber defense. We model the enterprise attack surface as a Markov decision process (MDP) where states summarize alerts, asset exposure, and service health, and actions represent real response steps (e.g., isolate a host, rotate credentials, ratelimit an API, block an account, or trigger recovery). RLShield learns coordinated policies across multiple agents (assets or service groups) and optimizes a risk-sensitive objective that balances containment speed, business disruption, and response cost. We also include a game-aware evaluation that tests policies against adaptive attackers and reports operational outcomes, not only reward. Experiments show that RLShield reduces time-to-containment and residual exposure while keeping disruption within a fixed response budget, outperforming static rule baselines and single-agent RL under the same constraints. These results suggest that multi-agent, cost-aware RL can provide a deployable layer for automated response in financial security operations.

Srikumar Nayak

Incedo Inc, USA

Autonomous Cyber DefenseCybersecurityMulti-Agent Reinforcement LearningConstrained RL
AskPDF
Feb 26, 2026

Learning-based Multi-agent Race Strategies in Formula 1

In Formula 1, race strategies are adapted according to evolving race conditions and competitors' actions. This paper proposes a reinforcement learning approach for multi-agent race strategy optimization. Agents learn to balance energy management, tire degradation, aerodynamic interaction, and pit-stop decisions. Building on a pre-trained single-agent policy, we introduce an interaction module that accounts for the behavior of competitors. The combination of the interaction module and a self-play training scheme generates competitive policies, and agents are ranked based on their relative performance. Results show that the agents adapt pit timing, tire selection, and energy allocation in response to opponents, achieving robust and consistent race performance. Because the framework relies only on information available during real races, it can support race strategists' decisions before and during races.

Giona Fieni, Joschua Wüthrich, Marc-Philippe Neumann +1

Autonomous RacingMulti-Agent Reinforcement Learning
AskPDF
Feb 26, 2026

Pixel2Catch: Multi-Agent Sim-to-Real Transfer for Agile Manipulation with a Single RGB Camera

To catch a thrown object, a robot must be able to perceive the object's motion and generate control actions in a timely manner. Rather than explicitly estimating the object's 3D position, this work focuses on a novel approach that recognizes object motion using pixel-level visual information extracted from a single RGB image. Such visual cues capture changes in the object's position and scale, allowing the policy to reason about the object's motion. Furthermore, to achieve stable learning in a high-DoF system composed of a robot arm equipped with a multi-fingered hand, we design a heterogeneous multi-agent reinforcement learning framework that defines the arm and hand as independent agents with distinct roles. Each agent is trained cooperatively using role-specific observations and rewards, and the learned policies are successfully transferred from simulation to the real world.

Seongyong Kim, Junhyeon Cho, Kang-Won Lee +1

Dongguk University

Robotic ManipulationDynamic Robotic ManipulationVision-Based Robot ControlSim-to-Real TransferMulti-Agent Reinforcement LearningRobotic Grasping
AskPDF
Feb 25, 2026

Hierarchical Lead Critic based Multi-Agent Reinforcement Learning

Cooperative Multi-Agent Reinforcement Learning (MARL) solves complex tasks that require coordination from multiple agents, but is often limited to either local (independent learning) or global (centralized learning) perspectives. In this paper, we introduce a novel sequential training scheme and MARL architecture, which learns from multiple perspectives on different hierarchy levels. We propose the Hierarchical Lead Critic (HLC) - inspired by natural emerging distributions in team structures, where following high-level objectives combines with low-level execution. HLC demonstrates that introducing multiple hierarchies, leveraging local and global perspectives, can lead to improved performance with high sample efficiency and robust policies. Experimental results conducted on cooperative, non-communicative, and partially observable MARL benchmarks demonstrate that HLC outperforms single hierarchy baselines and scales robustly with increasing amounts of agents and difficulty.

David Eckel, Henri Meeß

Fraunhofer Institute IVI, Ingolstadt, Germany

Multi-Agent Reinforcement LearningCooperative MARLHierarchical RLSequential MARL
AskPDF