Graph-based multi-agent reinforcement learning (MARL) enables coordinated behavior under partial observability by modeling agents as nodes and communication links as edges. While recent methods excel at learning sparse coordination graphs-determining who communicates with whom-they do not address what information should be transmitted under hard bandwidth constraints. We study this bandwidth-limited regime and show that naive dimensionality reduction consistently degrades coordination performance. Hard bandwidth constraints force selective encoding, but deterministic projections lack mechanisms to control how compression occurs. We introduce Bandwidth-constrained Variational Message Encoding (BVME), a lightweight module that treats messages as samples from learned Gaussian posteriors regularized via KL divergence to an uninformative prior. BVME's variational framework provides principled, tunable control over compression strength through interpretable hyperparameters, directly constraining the representations used for decision-making. Across SMACv1, SMACv2, and MPE benchmarks, BVME achieves comparable or superior performance while using 67--83% fewer message dimensions, with gains most pronounced on sparse graphs where message quality critically impacts coordination. Ablations reveal U-shaped sensitivity to bandwidth, with BVME excelling at extreme ratios while adding minimal overhead.
This work presents a conceptual study on the application of Multi-Agent Reinforcement Learning (MARL) for decentralized control of unmanned aerial vehicles to relay a critical data package to a known position. For this purpose, a family of deterministic games is introduced, designed for scaling studies for MARL. A robust baseline policy is proposed, which is based on restricting agent motion envelopes and applying Dijkstra's algorithm. Experimental results show that two off-the-shelf MARL algorithms perform competitively with the baseline for a small number of agents, but scalability issues arise as the number of agents increase.
Collaborative pursuit-evasion in cluttered environments presents significant challenges due to sparse rewards and constrained Fields of View (FOV). Standard Multi-Agent Reinforcement Learning (MARL) often suffers from inefficient exploration and fails to scale to large scenarios. We propose PGF-MAPPO (Path-Guided Frontier MAPPO), a hierarchical framework bridging topological planning with reactive control. To resolve local minima and sparse rewards, we integrate an A*-based potential field for dense reward shaping. Furthermore, we introduce Directional Frontier Allocation, combining Farthest Point Sampling (FPS) with geometric angle suppression to enforce spatial dispersion and accelerate coverage. The architecture employs a parameter-shared decentralized critic, maintaining O(1) model complexity suitable for robotic swarms. Experiments demonstrate that PGF-MAPPO achieves superior capture efficiency against faster evaders. Policies trained on 10x10 maps exhibit robust zero-shot generalization to unseen 20x20 environments, significantly outperforming rule-based and learning-based baselines.
Multi-Agent Reinforcement Learning (MARL) is commonly deployed in settings where agents are trained via self-play with homogeneous teammates, often using parameter sharing and a single policy architecture. This opens the question: to what extent do self-play PPO agents learn general coordination strategies grounded in the underlying game, compared to overfitting to their training partners' behaviors? This paper investigates the question using the Heterogeneous Multi-Agent Challenge (HeMAC) environment, which features distinct Observer and Drone agents with complementary capabilities. We introduce Rotating Policy Training (RPT), an approach that rotates heterogeneous teammate policies of different learning algorithms during training, to expose the agent to a broader range of partner strategies. When playing alongside a withheld teammate policy (DDQN), we find that RPT achieves similar performance to a standard self-play baseline, IPPO, where all agents were trained sharing a single PPO policy. This result indicates that in this heterogeneous multi-agent setting, the IPPO baseline generalizes to novel teammate algorithms despite not experiencing teammate diversity during training. This shows that a simple IPPO baseline may possess the level of generalization to novel teammates that a diverse training regimen was designed to achieve.
The deployment of Unmanned Aerial Vehicle (UAV) swarms as dynamic communication relays is critical for next-generation tactical networks. However, operating in contested environments requires solving a complex trade-off, including maximizing system throughput while ensuring collision avoidance and resilience against adversarial jamming. Existing heuristic-based approaches often struggle to find effective solutions due to the dynamic and multi-objective nature of this problem. This paper formulates this challenge as a cooperative Multi-Agent Reinforcement Learning (MARL) problem, solved using the Centralized Training with Decentralized Execution (CTDE) framework. Our approach employs a centralized critic that uses global state information to guide decentralized actors which operate using only local observations. Simulation results show that our proposed framework significantly outperforms heuristic baselines, increasing the total system throughput by approximately 50% while simultaneously achieving a near-zero collision rate. A key finding is that the agents develop an emergent anti-jamming strategy without explicit programming. They learn to intelligently position themselves to balance the trade-off between mitigating interference from jammers and maintaining effective communication links with ground users.
Large language models (LLMs) are post-trained through reinforcement learning (RL) to evolve into Reasoning Language Models (RLMs), where the hallmark of this advanced reasoning is ``aha'' moments when they start to perform strategies, such as self-reflection and deep thinking, within chain of thoughts (CoTs). Motivated by this, this paper proposes a novel reinforced strategy injection mechanism (rSIM), that enables any LLM to become an RLM by employing a small planner to guide the LLM's CoT through the adaptive injection of reasoning strategies. To achieve this, the planner (leader agent) is jointly trained with an LLM (follower agent) using multi-agent RL (MARL), based on a leader-follower framework and straightforward rule-based rewards. Experimental results show that rSIM enables Qwen2.5-0.5B to become an RLM and significantly outperform Qwen2.5-14B. Moreover, the planner is generalizable: it only needs to be trained once and can be applied as a plug-in to substantially improve the reasoning capabilities of existing LLMs. In addition, the planner supports continual learning across various tasks, allowing its planning abilities to gradually improve and generalize to a wider range of problems.
Analysing learning behaviour in Multi-Agent Reinforcement Learning (MARL) environments is challenging, in particular with respect to \textit{individual} decision-making. Practitioners frequently tend to study or compare MARL algorithms from a qualitative perspective largely due to the inherent stochasticity in practical algorithms arising from random dithering exploration strategies, environment transition noise, and stochastic gradient updates to name a few. Traditional analytical approaches, such as replicator dynamics, often rely on mean-field approximations to remove stochastic effects, but this simplification, whilst able to provide general overall trends, might lead to dissonance between analytical predictions and actual realisations of individual trajectories. In this paper, we propose a novel perspective on MARL systems by modelling them as \textit{coupled stochastic dynamical systems}, capturing both agent interactions and environmental characteristics. Leveraging tools from dynamical systems theory, we analyse the stability and sensitivity of agent behaviour at individual level, which are key dimensions for their practical deployments, for example, in presence of strict safety requirements. This framework allows us, for the first time, to rigorously study MARL dynamics taking into consideration their inherent stochasticity, providing a deeper understanding of system behaviour and practical insights for the design and control of multi-agent learning processes.
Vehicle collisions remain a major challenge in large-scale mixed traffic systems, especially when human-driven vehicles (HVs) and robotic vehicles (RVs) interact under dynamic and uncertain conditions. Although Multi-Agent Reinforcement Learning (MARL) offers promising capabilities for traffic signal control, ensuring safety in such environments remains difficult. As a direct indicator of traffic risk, the collision rate must be well understood and incorporated into traffic control design. This study investigates the primary factors influencing collision rates in a MARL-governed Mixed Traffic Control (MTC) network. We examine three dimensions: total vehicle count, signalized versus unsignalized intersection configurations, and turning-movement strategies. Through controlled simulation experiments, we evaluate how each factor affects collision likelihood. The results show that collision rates are sensitive to traffic density, the level of signal coordination, and turning-control design. These findings provide practical insights for improving the safety and robustness of MARL-based mixed traffic control systems, supporting the development of intelligent transportation systems in which both efficiency and safety are jointly optimized.
The low-altitude intelligent networks (LAINs) emerge as a promising architecture for delivering low-latency and energy-efficient edge intelligence in dynamic and infrastructure-limited environments. By integrating unmanned aerial vehicles (UAVs), aerial base stations, and terrestrial base stations, LAINs can support mission-critical applications such as disaster response, environmental monitoring, and real-time sensing. However, these systems face key challenges, including energy-constrained UAVs, stochastic task arrivals, and heterogeneous computing resources. To address these issues, we propose an integrated air-ground collaborative network and formulate a time-dependent integer nonlinear programming problem that jointly optimizes UAV trajectory planning and task offloading decisions. The problem is challenging to solve due to temporal coupling among decision variables. Therefore, we design a hierarchical learning framework with two timescales. At the large timescale, a Vickrey-Clarke-Groves auction mechanism enables the energy-aware and incentive-compatible trajectory assignment. At the small timescale, we propose the diffusion-heterogeneous-agent proximal policy optimization, a generative multi-agent reinforcement learning algorithm that embeds latent diffusion models into actor networks. Each UAV samples actions from a Gaussian prior and refines them via observation-conditioned denoising, enhancing adaptability and policy diversity. Extensive simulations show that our framework outperforms baselines in energy efficiency, task success rate, and convergence performance.
Intraday surgical scheduling is a multi-objective decision problem under uncertainty-balancing elective throughput, urgent and emergency demand, delays, sequence-dependent setups, and overtime. We formulate the problem as a cooperative Markov game and propose a multi-agent reinforcement learning (MARL) framework in which each operating room (OR) is an agent trained with centralized training and decentralized execution. All agents share a policy trained via Proximal Policy Optimization (PPO), which maps rich system states to actions, while a within-epoch sequential assignment protocol constructs conflict-free joint schedules across ORs. A mixed-integer pre-schedule provides reference starting times for electives; we impose type-specific quadratic delay penalties relative to these references and a terminal overtime penalty, yielding a single reward that captures throughput, timeliness, and staff workload. In simulations reflecting a realistic hospital mix (six ORs, eight surgery types, random urgent and emergency arrivals), the learned policy outperforms six rule-based heuristics across seven metrics and three evaluation subsets, and, relative to an ex post MIP oracle, quantifies optimality gaps. Policy analytics reveal interpretable behavior-prioritizing emergencies, batching similar cases to reduce setups, and deferring lower-value electives. We also derive a suboptimality bound for the sequential decomposition under simplifying assumptions. We discuss limitations-including OR homogeneity and the omission of explicit staffing constraints-and outline extensions. Overall, the approach offers a practical, interpretable, and tunable data-driven complement to optimization for real-time OR scheduling.
Multi-agent reinforcement learning (MARL) has emerged as a promising paradigm for adaptive traffic signal control (ATSC) of multiple intersections. Existing approaches typically follow either a fully centralized or a fully decentralized design. Fully centralized approaches suffer from the curse of dimensionality, and reliance on a single learning server, whereas purely decentralized approaches operate under severe partial observability and lack explicit coordination resulting in suboptimal performance. These limitations motivate region-based MARL, where the network is partitioned into smaller, tightly coupled intersections that form regions, and training is organized around these regions. This paper introduces a Semi-Centralized Training, Decentralized Execution (SEMI-CTDE) architecture for multi intersection ATSC. Within each region, SEMI-CTDE performs centralized training with regional parameter sharing and employs composite state and reward formulations that jointly encode local and regional information. The architecture is highly transferable across different policy backbones and state-reward instantiations. Building on this architecture, we implement two models with distinct design objectives. A multi-perspective experimental analysis of the two implemented SEMI-CTDE-based models covering ablations of the architecture's core elements including rule based and fully decentralized baselines shows that they achieve consistently superior performance and remain effective across a wide range of traffic densities and distributions.
We present a comparative study of multi-agent reinforcement learning (MARL) algorithms for cooperative warehouse robotics. We evaluate QMIX and IPPO on the Robotic Warehouse (RWARE) environment and a custom Unity 3D simulation. Our experiments reveal that QMIX's value decomposition significantly outperforms independent learning approaches (achieving 3.25 mean return vs. 0.38 for advanced IPPO), but requires extensive hyperparameter tuning -- particularly extended epsilon annealing (5M+ steps) for sparse reward discovery. We demonstrate successful deployment in Unity ML-Agents, achieving consistent package delivery after 1M training steps. While MARL shows promise for small-scale deployments (2-4 robots), significant scaling challenges remain. Code and analyses: https://pallman14.github.io/MARL-QMIX-Warehouse-Robots/
The growing demand for robust, scalable wireless networks in the 5G-and-beyond era has led to the deployment of Unmanned Aerial Vehicles (UAVs) as mobile base stations to enhance coverage in dense urban and underserved rural areas. This paper presents a Multi-Agent Deep Reinforcement Learning (MADRL) framework that integrates Proximal Policy Optimization (MAPPO), Multi-Agent Deep Deterministic Policy Gradient (MADDPG), and Multi-Agent Deep Q-Networks (MADQN) to jointly optimize UAV positioning, resource allocation, Quality of Service (QoS), and energy efficiency through 5G network slicing. The framework adopts Centralized Training with Decentralized Execution (CTDE), enabling autonomous real-time decision-making while preserving global coordination. Users are prioritized into Premium (A), Silver (B), and Bronze (C) slices with distinct QoS requirements. Experiments in realistic urban and rural scenarios show that MAPPO achieves the best overall QoS-energy tradeoff, especially in interference-rich environments; MADDPG offers more precise continuous control and can attain slightly higher SINR in open rural settings at the cost of increased energy usage; and MADQN provides a computationally efficient baseline for discretized action spaces. These findings demonstrate that no single MARL algorithm is universally dominant; instead, algorithm suitability depends on environmental topology, user density, and service requirements. The proposed framework highlights the potential of MARL-driven UAV systems to enhance scalability, reliability, and differentiated QoS delivery in next-generation wireless networks.
The deployment of multi-agent systems in dynamic, adversarial environments like robotic soccer necessitates real-time decision-making, sophisticated cooperation, and scalable algorithms to avoid the curse of dimensionality. While Reinforcement Learning (RL) offers a promising framework, existing methods often struggle with the multi-granularity of tasks (long-term strategy vs. instant actions) and the complexity of large-scale agent interactions. This paper presents a unified Multi-Agent Reinforcement Learning (MARL) framework that addresses these challenges. First, we establish a baseline using Proximal Policy Optimization (PPO) within a client-server architecture for real-time action scheduling, with PPO demonstrating superior performance (4.32 avg. goals, 82.9% ball control). Second, we introduce a Hierarchical RL (HRL) structure based on the options framework to decompose the problem into a high-level trajectory planning layer (modeled as a Semi-Markov Decision Process) and a low-level action execution layer, improving global strategy (avg. goals increased to 5.26). Finally, to ensure scalability, we integrate mean-field theory into the HRL framework, simplifying many-agent interactions into a single agent vs. the population average. Our mean-field actor-critic method achieves a significant performance boost (5.93 avg. goals, 89.1% ball control, 92.3% passing accuracy) and enhanced training stability. Extensive simulations of 4v4 matches in the Webots environment validate our approach, demonstrating its potential for robust, scalable, and cooperative behavior in complex multi-agent domains.
Multi-Agent Reinforcement Learning (MARL) is a branch of machine learning in which agents interact and learn optimal policies through trial and error, addressing complex scenarios where multiple agents interact and learn in the same environment at the same time. Analyzing and understanding these complex interactions is challenging, and existing analysis methods are limited in their ability to fully reflect and interpret this complexity. To address these challenges, we provide MARLViz, a visual analytics system for visualizing and analyzing the policies and interactions of agents in MARL environments. The system is designed to visually show the difference in behavior of agents under different environment settings and help users understand complex interaction patterns. In this study, we analyzed agents with similar behaviors and selected scenarios to understand the interactions of the agents, which made it easier to understand the strategies of agents in MARL.
Multi-agent reinforcement learning (MARL), as a thriving field, explores how multiple agents independently make decisions in a shared dynamic environment. Due to environmental uncertainties, policies in MARL must remain robust to tackle the sim-to-real gap. We focus on robust two-player zero-sum Markov games (TZMGs) in offline settings, specifically on tabular robust TZMGs (RTZMGs). We propose a model-based algorithm (\textit{RTZ-VI-LCB}) for offline RTZMGs, which is optimistic robust value iteration combined with a data-driven Bernstein-style penalty term for robust value estimation. By accounting for distribution shifts in the historical dataset, the proposed algorithm establishes near-optimal sample complexity guarantees under partial coverage and environmental uncertainty. An information-theoretic lower bound is developed to confirm the tightness of our algorithm's sample complexity, which is optimal regarding both state and action spaces. To the best of our knowledge, RTZ-VI-LCB is the first to attain this optimality, sets a new benchmark for offline RTZMGs, and is validated experimentally.
The thriving field of multi-agent reinforcement learning (MARL) studies how a group of interacting agents make decisions autonomously in a shared dynamic environment. Existing theoretical studies in this area suffer from at least two of the following obstacles: memory inefficiency, the heavy dependence of sample complexity on the long horizon and the large state space, the high computational complexity, non-Markov policy, non-Nash policy, and high burn-in cost. In this work, we take a step towards settling this problem by designing a model-free self-play algorithm \emph{Memory-Efficient Nash Q-Learning (ME-Nash-QL)} for two-player zero-sum Markov games, which is a specific setting of MARL. ME-Nash-QL is proven to enjoy the following merits. First, it can output an $\varepsilon$-approximate Nash policy with space complexity $O(SABH)$ and sample complexity $\widetilde{O}(H^4SAB/\varepsilon^2)$, where $S$ is the number of states, $\{A, B\}$ is the number of actions for two players, and $H$ is the horizon length. It outperforms existing algorithms in terms of space complexity for tabular cases, and in terms of sample complexity for long horizons, i.e., when $\min\{A, B\}\ll H^2$. Second, ME-Nash-QL achieves the lowest computational complexity $O(T\mathrm{poly}(AB))$ while preserving Markov policies, where $T$ is the number of samples. Third, ME-Nash-QL also achieves the best burn-in cost $O(SAB\,\mathrm{poly}(H))$, whereas previous algorithms have a burn-in cost of at least $O(S^3 AB\,\mathrm{poly}(H))$ to attain the same level of sample complexity with ours.
A clearer understanding of when coordination emerges, fluctuates, or collapses in decentralized multi-agent reinforcement learning (MARL) is increasingly sought in order to characterize the dynamics of multi-agent learning systems. We revisit fully independent Q-learning (IQL) as a minimal decentralized testbed and run large-scale experiments across environment size L and agent density rho. We construct a phase map using two axes - the cooperative success rate (CSR) and a stability index derived from TD-error variance - revealing three distinct regimes: a coordinated and stable phase, a fragile transition region, and a jammed or disordered phase. A sharp double Instability Ridge separates these regimes and corresponds to persistent kernel drift, the time-varying shift of each agent's effective transition kernel induced by others' policy updates. Synchronization analysis further shows that temporal alignment is required for sustained cooperation, and that competition between drift and synchronization generates the fragile regime. Removing agent identifiers eliminates drift entirely and collapses the three-phase structure, demonstrating that small inter-agent asymmetries are a necessary driver of drift. Overall, the results show that decentralized MARL exhibits a coherent phase structure governed by the interaction between scale, density, and kernel drift, suggesting that emergent coordination behaves as a distribution-interaction-driven phase phenomenon.
Multi-Agent Reinforcement Learning (MARL) holds significant promise for enabling cooperative driving among Connected and Automated Vehicles (CAVs). However, its practical application is hindered by a critical limitation, i.e., insufficient fault tolerance against observational faults. Such faults, which appear as perturbations in the vehicles' perceived data, can substantially compromise the performance of MARL-based driving systems. Addressing this problem presents two primary challenges. One is to generate adversarial perturbations that effectively stress the policy during training, and the other is to equip vehicles with the capability to mitigate the impact of corrupted observations. To overcome the challenges, we propose a fault-tolerant MARL method for cooperative on-ramp vehicles incorporating two key agents. First, an adversarial fault injection agent is co-trained to generate perturbations that actively challenge and harden the vehicle policies. Second, we design a novel fault-tolerant vehicle agent equipped with a self-diagnosis capability, which leverages the inherent spatio-temporal correlations in vehicle state sequences to detect faults and reconstruct credible observations, thereby shielding the policy from misleading inputs. Experiments in a simulated highway merging scenario demonstrate that our method significantly outperforms baseline MARL approaches, achieving near-fault-free levels of safety and efficiency under various observation fault patterns.
The integration of renewable energy resources in rural areas, such as dairy farming communities, enables decentralized energy management through Peer-to-Peer (P2P) energy trading. This research highlights the role of P2P trading in efficient energy distribution and its synergy with advanced optimization techniques. While traditional rule-based methods perform well under stable conditions, they struggle in dynamic environments. To address this, Multi-Agent Reinforcement Learning (MARL), specifically Proximal Policy Optimization (PPO) and Deep Q-Networks (DQN), is combined with community/distributed P2P trading mechanisms. By incorporating auction-based market clearing, a price advisor agent, and load and battery management, the approach achieves significant improvements. Results show that, compared to baseline models, DQN reduces electricity costs by 14.2% in Ireland and 5.16% in Finland, while increasing electricity revenue by 7.24% and 12.73%, respectively. PPO achieves the lowest peak hour demand, reducing it by 55.5% in Ireland, while DQN reduces peak hour demand by 50.0% in Ireland and 27.02% in Finland. These improvements are attributed to both MARL algorithms and P2P energy trading, which together results in electricity cost and peak hour demand reduction, and increase electricity selling revenue. This study highlights the complementary strengths of DQN, PPO, and P2P trading in achieving efficient, adaptable, and sustainable energy management in rural communities.
Dynamic sleep mode optimization (SMO) in millimeter-wave (mmWave) networks is essential for maximizing energy efficiency (EE) under stringent quality-of-service (QoS) constraints. However, existing optimization and reinforcement learning (RL) approaches rely on aggregated, static base station (BS) traffic models that fail to capture non-stationary traffic dynamics and suffer from large state-action spaces, limiting real-world deployment. To address these challenges, this paper proposes a multi-agent deep reinforcement learning (MARL) framework using a Double Deep Q-Network (DDQN), referred to as MARL-DDQN, for adaptive SMO in a 3D urban environment with a time-varying and community-based user equipment (UE) mobility model. Unlike conventional single-agent RL, MARL-DDQN enables scalable, distributed decision-making with minimal signaling overhead. A realistic BS power consumption model and beamforming are integrated to accurately quantify EE, while QoS is defined in terms of throughput. The method adapts SMO policies to maximize EE while mitigating inter-cell interference and ensuring throughput fairness. Simulations show that MARL-DDQN outperforms state-of-the-art strategies, including All On, iterative QoS-aware load-based (IT-QoS-LB), MARL-DDPG, and MARL-PPO, achieving up to 0.60 Mbit/Joule EE, 8.5 Mbps 10th-percentile throughput, and meeting QoS constraints 95% of the time under dynamic scenarios.
Multi-agent reinforcement learning (MARL) has been increasingly adopted in many real-world applications. While MARL enables decentralized deployment on resource-constrained edge devices, it suffers from severe non-stationarity due to the synchronous updates of agent policies. This non stationarity results in unstable training and poor policy con vergence, especially as the number of agents increases. In this paper, we propose RELED, a scalable MARL framework that integrates large language model (LLM)-driven expert demonstrations with autonomous agent exploration. RELED incorporates a Stationarity-Aware Expert Demonstration module, which leverages theoretical non-stationarity bounds to enhance the quality of LLM-generated expert trajectories, thus providing high reward and training-stable samples for each agent. Moreover, a Hybrid Expert-Agent Policy Optimization module adaptively balances each agent's learning from both expert-generated and agent-generated trajectories, accelerating policy convergence and improving generalization. Extensive experiments with real city networks based on OpenStreetMap demonstrate that RELED achieves superior performance compared to state-of-the-art MARL methods.
Cooperative Multi-Agent Reinforcement Learning (MARL) faces two major design bottlenecks: crafting dense reward functions and constructing curricula that avoid local optima in high-dimensional, non-stationary environments. Existing approaches rely on fixed heuristics or use Large Language Models (LLMs) directly in the control loop, which is costly and unsuitable for real-time systems. We propose MAESTRO (Multi-Agent Environment Shaping through Task and Reward Optimization), a framework that moves the LLM outside the execution loop and uses it as an offline training architect. MAESTRO introduces two generative components: (i) a semantic curriculum generator that creates diverse, performance-driven traffic scenarios, and (ii) an automated reward synthesizer that produces executable Python reward functions adapted to evolving curriculum difficulty. These components guide a standard MARL backbone (MADDPG) without increasing inference cost at deployment. We evaluate MAESTRO on large-scale traffic signal control (Hangzhou, 16 intersections) and conduct controlled ablations. Results show that combining LLM-generated curricula with LLM-generated reward shaping yields improved performance and stability. Across four seeds, the full system achieves +4.0% higher mean return (163.26 vs. 156.93) and 2.2% better risk-adjusted performance (Sharpe 1.53 vs. 0.70) over a strong curriculum baseline. These findings highlight LLMs as effective high-level designers for cooperative MARL training.
Inter-agent communication serves as an effective mechanism for enhancing performance in collaborative multi-agent reinforcement learning(MARL) systems. However, the inherent communication latency in practical systems induces both action decision delays and outdated information sharing, impeding MARL performance gains, particularly in time-critical applications like autonomous driving. In this work, we propose a Value-of-Information aware Low-latency Communication(VIL2C) scheme that proactively adjusts the latency distribution to mitigate its effects in MARL systems. Specifically, we define a Value of Information (VOI) metric to quantify the importance of delayed message transmission based on each delayed message's importance. Moreover, we propose a progressive message reception mechanism to adaptively adjust the reception duration based on received messages. We derive the optimized VoI aware resource allocation and theoretically prove the performance advantage of the proposed VIL2C scheme. Extensive experiments demonstrate that VIL2C outperforms existing approaches under various communication conditions. These gains are attributed to the low-latency transmission of high-VoI messages via resource allocation and the elimination of unnecessary waiting periods via adaptive reception duration.
By leveraging tool-augmented Multimodal Large Language Models (MLLMs), multi-agent frameworks are driving progress in video understanding. However, most of them adopt static and non-learnable tool invocation mechanisms, which limit the discovery of diverse clues essential for robust perception and reasoning regarding temporally or spatially complex videos. To address this challenge, we propose a novel Multi-agent system for video understanding, namely VideoChat-M1. Instead of using a single or fixed policy, VideoChat-M1 adopts a distinct Collaborative Policy Planning (CPP) paradigm with multiple policy agents, which comprises three key processes. (1) Policy Generation: Each agent generates its unique tool invocation policy tailored to the user's query; (2) Policy Execution: Each agent sequentially invokes relevant tools to execute its policy and explore the video content; (3) Policy Communication: During the intermediate stages of policy execution, agents interact with one another to update their respective policies. Through this collaborative framework, all agents work in tandem, dynamically refining their preferred policies based on contextual insights from peers to effectively respond to the user's query. Moreover, we equip our CPP paradigm with a concise Multi-Agent Reinforcement Learning (MARL) method. Consequently, the team of policy agents can be jointly optimized to enhance VideoChat-M1's performance, guided by both the final answer reward and intermediate collaborative process feedback. Extensive experiments demonstrate that VideoChat-M1 achieves SOTA performance across eight benchmarks spanning four tasks. Notably, on LongVideoBench, our method outperforms the SOTA model Gemini 2.5 pro by 3.6% and GPT-4o by 15.6%.
In multi-agent systems, explicit cognition of teammates' decision logic serves as a critical factor in facilitating coordination. Communication (i.e., ``\textit{Tell}'') can assist in the cognitive development process by information dissemination, yet it is inevitably subject to real-world constraints such as noise, latency, and attacks. Therefore, building the understanding of teammates' decisions without communication remains challenging. To address this, we propose a novel non-communication MARL framework that realizes the construction of cognition through local observation-based modeling (i.e., \textit{``Think''}). Our framework enables agents to model teammates' \textbf{active inference} process. At first, the proposed method produces three teammate portraits: perception-belief-action. Specifically, we model the teammate's decision process as follows: 1) Perception: observing environments; 2) Belief: forming beliefs; 3) Action: making decisions. Then, we selectively integrate the belief portrait into the decision process based on the accuracy and relevance of the perception portrait. This enables the selection of cooperative teammates and facilitates effective collaboration. Extensive experiments on the SMAC, SMACv2, MPE, and GRF benchmarks demonstrate the superior performance of our method.
Cooperative multi-agent reinforcement learning (MARL) commonly adopts centralized training with decentralized execution (CTDE), where centralized critics leverage global information to guide decentralized actors. However, centralized-decentralized mismatch (CDM) arises when the suboptimal behavior of one agent degrades others' learning. Prior approaches mitigate CDM through value decomposition, but linear decompositions allow per-agent gradients at the cost of limited expressiveness, while nonlinear decompositions improve representation but require centralized gradients, reintroducing CDM. To overcome this trade-off, we propose the multi-agent cross-entropy method (MCEM), combined with monotonic nonlinear critic decomposition (NCD). MCEM updates policies by increasing the probability of high-value joint actions, thereby excluding suboptimal behaviors. For sample efficiency, we extend off-policy learning with a modified k-step return and Retrace. Analysis and experiments demonstrate that MCEM outperforms state-of-the-art methods across both continuous and discrete action benchmarks.
Spatial task allocation in systems such as multi-robot delivery or ride-sharing requires balancing efficiency with fair service across tasks. Greedy assignment policies that match each agent to its highest-preference or lowest-cost task can maximize efficiency but often create inequities: some tasks receive disproportionately favorable service (e.g., shorter delays or better matches), while others face long waits or poor allocations. We study fairness in heterogeneous multi-agent systems where tasks vary in preference alignment and urgency. Most existing approaches either assume centralized coordination or largely ignore fairness under partial observability. Distinct from this prior work, we establish a connection between the Eisenberg-Gale (EG) equilibrium convex program and decentralized, partially observable multi-agent learning. Building on this connection, we develop two equilibrium-informed algorithms that integrate fairness and efficiency: (i) a multi-agent reinforcement learning (MARL) framework, EG-MARL, whose training is guided by a centralized EG equilibrium assignment algorithm; and (ii) a stochastic online optimization mechanism that performs guided exploration and subset-based fair assignment as tasks are discovered. We evaluate on Multi-Agent Particle Environment (MPE) simulations across varying team sizes against centralized EG, Hungarian, and Min-Max distance baselines, and also present a Webots-based warehouse proof-of-concept with heterogeneous robots. Both methods preserve the fairness-efficiency balance of the EG solution under partial observability, with EG-MARL achieving near-centralized coordination and reduced travel distances, and the online mechanism enabling real-time allocation with competitive fairness.
Episodic rewards present a significant challenge in reinforcement learning. While intrinsic reward methods have demonstrated effectiveness in single-agent rein-forcement learning scenarios, their application to multi-agent reinforcement learn-ing (MARL) remains problematic. The primary difficulties stem from two fac-tors: (1) the exponential sparsity of joint action trajectories that lead to rewards as the exploration space expands, and (2) existing methods often fail to account for joint actions that can influence team states. To address these challenges, this paper introduces Mutual Intrinsic Reward (MIR), a simple yet effective enhancement strategy for MARL with extremely sparse rewards like episodic rewards. MIR incentivizes individual agents to explore actions that affect their teammates, and when combined with original strategies, effectively stimulates team exploration and improves algorithm performance. For comprehensive experimental valida-tion, we extend the representative single-agent MiniGrid environment to create MiniGrid-MA, a series of MARL environments with sparse rewards. Our evalu-ation compares the proposed method against state-of-the-art approaches in the MiniGrid-MA setting, with experimental results demonstrating superior perfor-mance.
Conflict resolution and consensus building represent critical challenges in multi-agent systems, negotiations, and collaborative decision-making processes. This paper introduces Dialogue Diplomats, a novel end-to-end multi-agent reinforcement learning (MARL) framework designed for automated conflict resolution and consensus building in complex, dynamic environments. The proposed system integrates advanced deep reinforcement learning architectures with dialogue-based negotiation protocols, enabling autonomous agents to engage in sophisticated conflict resolution through iterative communication and strategic adaptation. We present three primary contributions: first, a novel Hierarchical Consensus Network (HCN) architecture that combines attention mechanisms with graph neural networks to model inter-agent dependencies and conflict dynamics. second, a Progressive Negotiation Protocol (PNP) that structures multi-round dialogue interactions with adaptive concession strategies; and third, a Context-Aware Reward Shaping mechanism that balances individual agent objectives with collective consensus goals.