Multi-Agent Reinforcement Learning

Also known as MARL

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

402 papers37 papers in the last four weeks, down 27% on the four weeks before. 0.3% of all new papers.

Oct 4, 2026

Orchestrating Level-KK Policies Against Unknown Opponents in Partially-Observable Dynamic Games

Level-KK reasoning generates a hierarchy of policies specialized to opponents with different reasoning levels. When an opponent's level is unknown, a common deployment rule estimates that level and selects the corresponding response. In a dynamic, partially-observed game, this selection is repeated, with each choice shaping subsequent states and observations. The response associated with the most likely opponent level need not maximize expected return from the current history. We formulate this deployment problem as dynamic orchestration of a fixed, pretrained policy library in a partially observable Markov game. We compare classification-based orchestrators (CBOs) trained using offline data or on-policy data aggregation with a reinforcement-learning-based orchestrator (RLBO) trained to maximize expected discounted return. In pursuit-evasion experiments, on-policy training improves classification and return, yet RLBO achieves higher return than the on-policy and offline CBOs. Given a pretrained library, RLBO also reaches performance comparable to a policy trained directly over the pursuers' action space with fewer training timesteps. These findings support treating a hierarchy of level-KK policies as a resource for orchestration, not a prescription for deployment.
Oct 3, 2026

Multi-Agent Spectrum Sharing

This project explores how multiple cognitive radars can learn to share limited wireless spectrum with other radio users without interfering with one another. Using machine learning (ML), each device independently decides where and how widely to transmit within a fixed 100 MHz band. The system analyzes real or simulated signal activity to detect which parts of the spectrum are currently in use and which are open. Based on this information, the devices adapt their transmission choices to avoid crowded frequencies while making efficient use of available space. The goal is to develop a flexible, scalable approach to spectrum sharing that could support future wireless communication systems. Experimental results using both over-the-air software-defined radio (SDR) recordings and simulated environments demonstrate that the proposed meta-learning approach consistently balances competing objectives better than conventional reinforcement learning (RL) methods in multi-agent spectrum-sharing scenarios. Across five multi-agent benchmark environments, our proposed method achieved the highest average reward among the primary baseline algorithms while simultaneously maintaining low collision rates and stable transmission behavior.
Oct 3, 2026

Playing social deduction games with reinforcement fine-tuned large language models

Reinforcement fine-tuning (RFT) is increasingly used in applications where large language models (LLMs) interact with humans and other agents. Here we use social deduction games to study how RFT changes LLMs' social behaviour. We let fine-tuned and base LLM agents play hidden-role games that require hidden-state inference, social reading and vote steering. Our results show that LLM agents do not reliably acquire social-deduction ability by directly optimizing terminal win--loss outcomes, suggesting that final game results provide a sparse and noisy signal for socially interactive learning. However, RFT is particularly effective at improving social reading, including tasks that require agents to infer hidden roles from public discussion, update beliefs over time and predict other agents' future decisions. We further show that RFT can also improve social influence, including tasks that require agents to steer votes, team approvals and collective decisions, although these gains depend more strongly on behaviourally specific rewards and structured interaction settings. Finally, we show that LLMs' ability to play social deduction games can be further improved through multi-agent social-cognitive reinforcement fine-tuning, which combines social-reading and social-influence signals during same-side multi-agent training. These learned behaviours also receive more favourable human evaluations of strategic competence, persuasiveness and social usefulness. Together, these results enrich our understanding of how RFT changes LLMs' social behaviour and provide a step toward a behavioural learning theory for machine social intelligence.
Oct 2, 2026

Permutation Robustness Is Not Enough: Action Collapse in Multi-Agent Transformer Policies

Transformer policies are attractive for multi-agent robot learning because self-attention can model interactions among agents. However, multi-agent teams are unordered, while transformers typically process agents as ordered token sequences. We study how this mismatch affects cooperative navigation policies under agent-order permutations. Our results show that low permutation error alone can be misleading: policies may appear robust simply because all agents choose the same action. We therefore evaluate policies using both permutation-consistency metrics and action-collapse diagnostics, including action diversity, same-action fraction, and maximum action frequency. A PPO-ID baseline yields non-collapsed behavior but remains order-sensitive, while strong equivariance regularization can still induce homogeneous behavior. A weak equivariance penalty improves the robustness while preserving more diverse actions for teams with N=3N=3 agents, whereas teams with N=4N=4 agents require substantially smaller regularization weights. These findings suggest that multi-agent transformer policies should be evaluated not only by return and permutation robustness, but also by whether they maintain non-collapsed, differentiated multi-agent behavior.
Oct 2, 2026

Turnover-Orthogonal Credit Assignment for Open-Team Multi-Agent Reinforcement Learning

Open-team multi-agent reinforcement learning studies cooperative systems in which agents may join, leave, or be replaced during an episode. In such settings, the team return changes both because agents choose useful actions and because the active population itself changes. Standard centralized critics and shared advantages often mix these two effects into one scalar credit signal, allowing surviving agents to be rewarded or penalized for exogenous turnover events outside their control. We introduce turnover-orthogonal credit assignment (TOCA), a value decomposition for open teams that separates action effects, pure turnover effects, and action--turnover interactions. Under exogenous turnover, the event-conditioned value admits a centered decomposition whose event-conditioned baseline removes the pure turnover component while preserving credit for actions that make the team robust to future replacements. We instantiate this idea with a permutation-invariant centralized critic over variable-size agent sets and event tokens, and derive both a counterfactual per-agent credit signal and a softly weighted interaction variant, TOCA-ββ, for high-variance control environments. Controlled diagnostic experiments show that TOCA improves return over event-aware MAPPO-style critics and that removing interaction credit substantially hurts performance. In a replacement-only Dynamic Spread benchmark, TOCA-ββ achieves the best mean return at high turnover rates and improves over its no-interaction ablation. These results suggest that explicitly separating turnover from action credit is a useful principle for robust learning in dynamic cooperative teams.
Oct 1, 2026

Flowing Faster to Coordinate: One-Step Online Multi-Agent Flow Policies

Multi-agent reinforcement learning (MARL) provides a powerful framework for learning coordinated behaviors through interactions with the environment. Developing MARL policies requires balancing expressive modeling of complex and multimodal action distributions with efficient training and execution. Generative policies, particularly diffusionbased policies, can faithfully capture complex and multimodal behaviors, but costly iterative sampling hinders their scalability in online multi-agent settings. We propose an Online MARL framework via one-step Flow model (OMAF) that combines expressive generative policies with efficient one-step action generation. OMAF employs a Transformer-based flow policy to capture complex coordination behaviors, while its approximate path score surrogate provides a principled route to synchronized flow policy optimization. To enable stable and sampleefficient learning, we further develop a joint optimization scheme coupling softmax Q-value estimation with a joint flow policy objective for coordinated policy learning. By eliminating iterative sampling, OMAF dramatically reduces training overhead without sacrificing policy expressiveness. Extensive experiments across 10 standard tasks from MPE and MAMuJoCo show that OMAF consistently achieves superior performance, with up to 3.4x higher returns and 10.5x sample efficiency improvement compared with baseline methods. These results validate the effectiveness of OMAF as an expressive and computationally efficient one-step flow policy paradigm for online MARL.
Sep 30, 2026

Meta-Multi-Agent Reinforcement Learning for Fast Adaptation of Interactive Policies with Applications to Autonomous Driving

This paper develops a meta-multi-agent reinforcement learning (meta-MARL) framework to enable fast adaptation of interactive policies in a multi-agent system (MAS). Meta-reinforcement learning (meta-RL) enables agents to rapidly adapt to new tasks/environments using a bi-level optimization mechanism. However, existing meta-RL generally focuses on single-agent systems. Extending these frameworks and algorithms to multi-agent systems poses additional challenges, as tasks are characterized by not only the environment but also agents' strategic interactions. To address these challenges, we model multi-agent reinforcement learning (MARL) problems as Markov games (MGs) and develop a meta-MARL framework for rapid interactive policy adaptation across a distribution of MGs. A new concept, called meta-NE, is defined to describe the desired solution concept in a meta-MARL problem. Sufficient conditions for the equivalence between a meta-NE and a stationary point of the gradient-play-based meta-MARL algorithm are established. Our evaluation on autonomous-driving tasks demonstrates that the proposed meta-MARL method achieves faster adaptation than pretrained MARL baselines, validating the effectiveness of our framework.
Sep 30, 2026

Beyond Supra-Competitive Outcomes: Collusive Behaviour in Deep Reinforcement Learning for Optimal Execution Games

In this paper, we extend earlier findings of supra-competitive outcomes in optimal-execution games by identifying a learned punitive mechanism that deters deviations and provides behavioural evidence of collusion. We investigate this mechanism in a two-player, finite-horizon Almgren-Chriss liquidation game. Independent proximal policy optimisation agents with access to within-episode price and action histories achieve costs below the Nash benchmark. We identify a profitable deviation by training against the mean learned liquidation schedule, then impose its first trade on one of the original agents. The opponent responds by accelerating liquidation. This response more than offsets the deviator's gain in every run and both player roles, while leaving the punisher's average payoff materially unchanged relative to not punishing under the same deviation. The punisher imposes greater losses on the deviator while preserving its own average payoff, despite the availability of more profitable, less punitive liquidation plans. Matching deviations and subsequent additional selling rise and later decline during training, while final policies retain an effective punitive response. We formalise two checks: whether punishment outweighs the gain from deviating, and whether the change in trading behaviour is large enough to account for the loss imposed. Both checks hold for the tested deviation. Together, these findings provide behavioural and economic evidence supporting a collusive interpretation of the learned supra-competitive outcomes.
Sep 29, 2026

PowerMarketJax: A JAX Benchmark Suite for Multi-Agent Reinforcement Learning in Power Markets

Power markets are a natural testbed for multi-agent reinforcement learning (MARL), where multiple self-interested participants repeatedly submit bids. A market-clearing mechanism then determines dispatch and prices subject to power grid constraints and market settlement rules. However, existing MARL environments typically focus on a single market setting, implement simplified clearing mechanisms, or rely on CPU-based optimization solvers that slow large-scale training and limit the systematic study of bidding strategies and market behavior. We introduce PowerMarketJax, a benchmark suite for MARL across five power markets: day-ahead wholesale, real-time balancing, ancillary services, peer-to-peer double auctions, and local flexibility. Each environment implements its own clearing, pricing, and settlement rules while providing a common framework for learning and evaluation. We find that learned bidding behavior depends strongly on the market design: independent learners can miss better strategies when gains require many agents to change together, when more profitable strategies lie beyond a region of lower profit, or when profits disappear as more agents adopt the same strategy. PowerMarketJax implements both market simulation and policy training in JAX, allowing the entire pipeline to run on the GPU with 1,024 X 1,200 parallelisms across both environments and market participants, achieving up to 33X speedup over CPU-based baselines. Our open-source benchmark is available at: https://github.com/powermarketjax/PowerMarketJax.
Sep 29, 2026

Regularized policy gradient with learned mixtures of Gaussians for games with continuous actions

Most successes of superhuman game-playing algorithms are in games with discrete actions, yet in auctions, robotics, sports, or trading, actions are nearly continuous. Prior techniques either rely on expert-designed discretizations or are sample inefficient. We present a scalable policy-gradient algorithm for large sequential games with continuous or mixed discrete and continuous actions. It combines magnetic mirror descent with a mixture of Gaussians reparametrization, trained via self-play. We show that it approximates equilibrium in games where gradient descent fails. In sequential games, it outperforms neural fictitious self-play and matches or outperforms the final strategies of policy space response oracles with 3.5--5.5×\times fewer samples. In heads-up no-limit Texas hold'em, it performs on par with Slumbot.
Sep 29, 2026

Learning to Harvest Without Collapse in a Regenerative Commons: A Lagrangian Framework

The tragedy of the commons poses a multi-agent safety problem: reward-seeking agents can deplete a shared resource, and cooperation among its users does not itself specify how much must be preserved. We make preservation an explicit requirement by formulating a regenerative commons as a constrained Markov game or a constrained multi-agent MDP with a designer-specified depletion budget. We develop a nonstationary Lagrangian framework that constructs a policy sequence from solutions of unconstrained games or cooperative control problems. Extending earlier time-average constructions, we introduce average-epoch solution concepts for reset episodes with discounted rewards and terminal costs. We prove a reward-independent feasibility certificate, cooperative feasibility and approximate optimality against feasible policy mixtures, and an extension to unbiased sampled costs. For self-interested agents, a constrained Nash certificate quantifies the price-dispersion term introduced by deviations that redistribute budget across epochs. Under the stated assumptions on solver accuracy and multiplier updates, these results give constrained policy-sequence guarantees using solutions of unconstrained problems. Experiments with constrained IPPO and MAPPO in a Gordon-Schaefer fishery examine how depletion budgets shape stock retention, harvest rewards, and price adaptation.
Sep 28, 2026

Fully Decentralized and Safety-Aware Multi-Agent Reinforcement Learning for Control on Networks

This paper develops a safe and fully decentralized multi-agent reinforcement learning (MARL) algorithm to solve a class of discrete-time control problems on networks, including the persistent monitoring problem. Fully decentralized control of agents, while offering numerous benefits, faces issues such as exponentially increasing sample complexity, lack of global information about the system, and challenges in coordinating between agents. To address these issues, this paper introduces a fully decentralized multi-agent reinforcement learning algorithm that integrates deep reinforcement learning with safety considerations. This method feeds a history of local observations of the network's state into two parallel neural-network branches: the graph encoder, which adds structural information and correlations among nodes, and a state estimator, which predicts the uncertainty at each node in the graph. Additionally, the result of feeding that input into an actor-critic network is passed through a discrete-time control barrier heuristic to reduce the likelihood that any node will be neglected. This approach enables teams of fully decentralized agents to solve challenging problems by increasing system awareness and incorporating built-in safety measures to prevent the adoption of potentially harmful control policies. Numerical results from a custom simulation environment demonstrate that the proposed algorithm achieves 26.3 percent lower average uncertainty than a centralized control policy and is within 1 percent of the uncertainty performance of a more computationally complex algorithm with added attention layers.
Sep 28, 2026

Persistent Partners Raise Prices Among Learning Agents

When pricing agents meet repeatedly on a platform, the platform decides who faces whom. We ask whether that choice moves the prices the agents learn, and whether a rise comes with learned punishment. In a pre-registered randomised experiment in the Bertrand duopoly of Calvano et al., each agent's price is set by a tabular Q-learning module, not by the small language model attached to it, and we randomise whether each agent keeps its partner, sees its rival's prices and can send messages. Keeping the same partner raises the level of profits, averaged over training, by 0.27 of the gap between competitive and monopoly profit (95% CI 0.20 to 0.35, all twenty paired runs positive), our registered primary result, and the resting price by 0.17 of the Nash-to-monopoly range (post hoc). A plain tabular learner reproduces the effect in all 25 further blocks, and there one permanent partner raises the level more than about three do (+0.23 against +0.05, exploratory). Where rival prices are hidden, the price-setting module cannot see a cut, so cannot punish it, yet the resting price rises as much and the rise lasts to the end of training, while with visible rivals it shrinks with longer training (post hoc). Where the rival is visible, a static best responder accounts for a third to a half of what a forced-deviation probe reads as punishment, on the starts where the rival can see the cut, and net of it the registered test of learned punishment is inconclusive. A test that looks only for punishment would thus miss the rise where the rival is hidden, while a check for profitable deviations flags most of those prices (post hoc). In an exploratory extension, untrained Qwen2.5 7B and 14B models under one prompt show the effect when the rival's price is left out of the prompt and inconsistently when it is shown, the 7B result replicating on fresh blocks, while two other model families show none.
Sep 28, 2026

Coordinated Lane-Level Variable Speed Limits and Ramp Metering for Successive Weaving Segments Considering Merging/Diverging Risks: A Hybrid Model Predictive Control and Multi-Agent Reinforcement Learning Approach

Successive weaving segments (SWSs) on urban expressways are bottlenecks prone to recurrent congestion and collisions, requiring fine-grained active traffic management (ATM). Existing approaches struggle to balance the adaptive performance of data-driven optimization with the resilience and transferability of model-based control. We propose a hybrid framework to coordinate lane-level variable speed limits (VSLs) and ramp metering across SWSs. First, we reconstruct L-METANET, a lane-level macroscopic traffic flow model that captures free and forced lane changes. Second, we combine XGBoost-SHAP with a random-parameters binary logit (RPBL) model to derive analytical equations for merging and diverging collision risks and formulate system cost and reward functions. Third, we develop MPC-STMAPPO, a hierarchical controller integrating model predictive control (MPC) and multi-agent reinforcement learning (MARL). Its upper MPC layer uses L-METANET for long-horizon rolling optimization and generates baseline commands; its lower spatiotemporal MAPPO (ST-MAPPO) layer, enhanced with Mamba cells and graph attention, produces residual actions for short-horizon adjustment. Real-world experiments on the 18-km Eastern Expressway in Changchun, China, show that L-METANET accurately reproduces lane-changing-induced flow redistribution and capacity drops, with state evolution aligned with ground truth. XGBoost-SHAP-RPBL achieves AUCs above 0.80 in most tasks, outperforming conventional logit models. MPC-STMAPPO converges faster and performs better across multiple metrics than MPC- and MARL-based baselines. Under randomly fluctuating demand, it also significantly outperforms pure MARL in generalization, demonstrating strong potential for industrial deployment.
Sep 27, 2026

Hierarchical Multi-agent Reinforcement Learning for Warehouse Robot Coordination under Communication Loss

In this paper, we propose a hierarchical multi-agent reinforcement learning framework for coordinating robot teams in warehouse environments under communication loss. We partition the robot team into groups, with centralized coordination within each group and distributed coordination across groups. Each group uses a recurrent predictor to estimate unavailable interaction information due to communication loss. A higher-level policy then generates a compact coordination reference that conditions the local control policy within each group. A predictive safety filter evaluates and modifies the proposed controls when they violate safety constraints. Simulation results show improved task completion under communication loss, reduced communication growth as the team size increases, and safe operation in the tested scenarios.
Sep 27, 2026

MA-JEPA: Joint-Embedding World Models for Multi-Agent Reinforcement Learning

World models improve sample efficiency by training policies on imagined trajectories, but their usefulness depends on learning representations that capture the information needed for future control. We study whether self-supervised joint-embedding prediction (JEPA) can provide this learning signal for multi-agent reinforcement learning. We introduce MA-JEPA, a stochastic world model that replaces observation reconstruction with prediction of target representations, enabling model-based multi-agent reinforcement learning with centralized training and decentralized execution. A categorical latent state and a causal Transformer are trained with posterior and action-conditioned dynamics prediction objectives and are then used for actor-critic learning from latent imagination. A training-only joint predictor conditions on all agents' local states and actions to predict each agent's next local observation embedding. These predictions are passed through the same local posterior used during real interaction with a centralized critic that is used only for value learning, with execution remaining decentralized. Our experiments show that this architecture performs strongly on SMAC, matching or exceeding the strongest reported comparator mean win rate on four of eight evaluated maps.
Sep 26, 2026

Improving LLM Collaboration via Multi-Agent Preference Learning

Several works have explored multi-agent reinforcement learning (MARL) in LLM collaboration. However, constructing reliable rewards is difficult in practice, as complete and accurate metrics are often unavailable and hard to aggregate. Preference learning provides an alternative by learning from comparative human or AI feedback. Yet, its extension to multi-agent systems remains underexplored. To address this gap, we formulate preference-based multi-agent systems (MAS) from decentralized and centralized collaboration perspectives. We also introduce a general multi-agent preference learning framework (MAPL) to solve these problems. MAPL allows iterative updates by comparing the current solution with decentralized or centralized solutions generated by various agents. We instantiate MAPL using MARL from human feedback (MARLHF) with a learned reward model and multi-agent direct preference optimization (MADPO). Experiments on collaborative writing, coding, tool use, and travel planning show that MAPL can improve collaboration quality and efficiency while approaching the performance of MARL with fixed, well-defined rewards. Within MAPL, MARLHF generally outperforms MADPO on most tasks but remains sensitive to data coverage, agent and comparator models, and the underlying MARL algorithms.
Sep 25, 2026

Interactive Distributionally Robust Multi-Agent Learning with General Function Approximation

Model misspecification poses a fundamental challenge in multi-agent reinforcement learning, where transition uncertainty can be amplified by strategic interactions among agents. Distributionally robust Markov games (DRMGs) provide a principled framework for addressing such uncertainty, yet existing methods often rely on restrictive assumptions or scale poorly to large state and joint action spaces. We study online learning in general-sum DRMGs with general function approximation and φφ-divergence uncertainty sets. We propose RoMEX-φφ, a model-free framework that integrates equilibrium-based exploration with dual fitted learning. Through a functional dual representation of the robust multi-agent Bellman operator, RoMEX-φφ enables tractable worst-case value estimation from nominal interaction data using a centered empirical robust discrepancy. We introduce the robust Multi-Agent Decoupling Coefficient (robust MADC) to characterize the intrinsic exploration complexity arising from strategic interactions and adversarial transition uncertainty. We establish sublinear robust regret guarantees governed by the robust MADC rather than explicitly by the state and joint action space sizes, replacing tabular dependence with intrinsic function-class complexity. Numerical experiments on a scalable general-sum DRMG under total variation uncertainty show that RoMEX-φφ is substantially more resilient to transition shifts than its non-robust counterpart while remaining competitive with an exact tabular robust baseline. Our results provide a scalable framework for distributionally robust multi-agent reinforcement learning with general function approximation.
Sep 25, 2026

Decentralized Master-Mind: Joint Action Refinement through Iterative Intent Denoising in Multi-Agent Pathfinding

Decentralized multi-agent path finding (MAPF) with communication requires agents to reach individual goals without collisions under partial observability. Learnable policies trained on expert data provide an effective approach to this problem. However, when several coordinated joint actions are valid in the same context, independently sampling from per-agent distributions can recombine locally valid choices into incompatible joint actions. This failure can arise from the final sampling mechanism even when the per-agent action distributions are learned correctly. DMM (Decentralized Master-Mind) addresses this by replacing one-shot action sampling with discrete, iterative refinement of action intents across communication rounds, inspired by denoising in diffusion models. Agents initialize random action intents and refine them through local communication, coupling their choices before commitment. DMM is pretrained with imitation learning on expert MAPF solutions and further optimized with MICPO, a critic-free group-relative reinforcement-learning method designed for multi-agent, multi-round action refinement. DMM generally achieves higher success rates and lower solution costs than the evaluated learnable baselines. On 1,600 MovingAI tasks, DMM fine-tuned with MICPO solves 1,598, the highest coverage among the evaluated methods, while achieving solution costs close to those of the strongest baselines. DMM also scales to over one million simultaneously acting agents in obstacle-rich environments. These results show that round-level intent refinement can improve joint-action coordination while preserving decentralized execution.
Sep 25, 2026

HySTAR: Anchored Hypergraphs for Stable Credit Assignment in Cooperative Multi-Agent Reinforcement Learning

Cooperative multi-agent reinforcement learning under partial observability and shared rewards requires assigning team outcomes to individual agents and high-order coalitions. A MAPPO-style critic compresses joint behavior into one global value, while critics that dynamically reconstruct the grouping topology change the mapping from agents and coalitions to value components as interactions or active agents evolve. We refer to this inconsistency as structural target drift. We introduce HySTAR, a MAPPO-based framework that separates adaptive representation learning from a temporally consistent high-order value-decomposition basis. HySTAR anchors an overlapping sparse hypergraph as a uniformly covered decomposition scaffold, uses a spatiotemporal encoder to represent physical and task-dependent interactions, and combines temporal and structural relevance to construct agent-specific advantages. Experiments on SMAC, GRF, Traffic Junction, and MPE demonstrate consistent improvements over MAPPO-style, value-factorization, and dynamic-grouping baselines. On the hardest SMAC settings, HySTAR achieves relative gains of 16.7% over MAPPO and 15.6% over HYGMA, ranks first on all six GRF scenarios, reduces Traffic Junction convergence epochs by up to 40.2% relative to MAGIC, and obtains the highest MPE episode rewards. Controlled topology, agent-death, neighborhood, and parameter analyses support the benefit of anchoring the decomposition scaffold while adapting the propagated representations.
Sep 24, 2026

Graph-Based Inference and Topology-Aware Multi-Agent Reinforcement Learning for Large-Scale Railway Network Management

Modern infrastructure asset management constitutes a complex sequential decision-making problem, characterized by long planning horizons and system-level interactions, such as spatial deterioration correlations and economies of scale. While deep reinforcement learning has shown promise in optimizing maintenance policies, scaling to real-world networks remains challenging. Centralized approaches become computationally intractable in large-scale systems, whereas decentralized approaches often fail to capture essential coordination mechanisms. To address these challenges, we propose a graph-based framework that integrates accurate environment modeling with scalable decision support. First, we employ a hierarchical Bayesian model leveraging a Gaussian Process on Graph kernel to infer a realistic, spatially correlated networked environment of railway maintenance planning from real-world data provided by the Swiss Federal Railways. Second, we introduce a topology-aware Multi-Agent Reinforcement Learning (MARL) framework by integrating graph neural networks and graph Transformers to optimize network-level policies. A central contribution of this work is the demonstration of scalability through zero-shot transfer learning: graph-based agents, trained only on small network portions, are successfully deployed in a zero-shot manner on large-scale unseen networks without any retraining. Numerical results indicate that the proposed method significantly outperforms optimized heuristics and standard MARL baselines, reducing computational training time while maintaining superior performance on large-scale networks.
Sep 23, 2026

Anchor and Perturb: Lazy Agent Remediation by Exploration Injection

Anchor and Perturb (AnP) is a lightweight framework that resolves multi-agent coordination failures by decoupling exploratory variance injection from recurrent manifold stability. Existing remediation strategies predominantly alter mixing network architectures or enforce simultaneous exploration across the collective, which inevitably precipitates severe temporal-difference penalties in non-monotonic reward spaces. Specifically, AnP isolates underperforming lazy agents and injects an asymmetric exploratory pulse into targeted coordinates whilst anchoring converged teammates to nominal greedy exploitation. Empirical telemetry benchmarks demonstrate that AnP successfully rescues collapsed joint policies (recovering from a 5% evaluation win rate nadir back to 85%) and facilitates escape from suboptimal coordination plateaus, sustaining peak win rates of 90% without requiring structural network modifications.
Sep 23, 2026

Turning Safety into Competence: Minimally Exploitable Robot Policies via Safety-Filtered Reinforcement Learning

Robots deployed for competitive tasks must outmaneuver their opponents without sacrificing safety. Existing approaches, including safe reinforcement learning (RL), train a single policy to achieve task success and avoid failures simultaneously. This coupling can complicate training and leave the learned policy exploitable by deliberate attacks. We propose Safety to Competence (S2C), a two-stage RL framework that separates safety synthesis from competitive task learning. We formulate competitive interactions as safety-critical Markov games and prove that perfect filtering preserves policy non-exploitability when all players commit to safe maneuvers. S2C learns a robust safety filter via adversarial RL, embeds it in the environment during task policy training, and retains the same filter at deployment. In simulated touchdown games, S2C outperforms eight safe RL baselines, achieving the highest win rate and Elo rating, and the lowest exploitability. Hardware stress tests against a human opponent confirm S2C's competence.
Sep 23, 2026

FairTest: Search-Based Fairness Testing for Multi-Agent Reinforcement Learning Systems

Multi-agent Reinforcement Learning (MARL) trains a team of agents that share one environment and learn their policies together. Training maximizes the team return, and a high return does not imply that the rewards are shared fairly among the agents in every episode. Testing is an established way to discover the failures of deep reinforcement learning, yet few methods address the fairness of MARL. In this work, we propose FairTest, a search-based testing approach that seeks the unfair executions of a MARL policy. The design combines search guidance with test prioritization. The guidance scores each candidate with three fitness functions. One measures the fairness of the runs already performed, another predicts the fairness from abstract states and fairness features, and the third reads the decision uncertainty from the policy. Crossover and mutation derive further candidates from the observed executions. The prioritization ranks the candidates by the predicted fairness and the decision uncertainty, so that the runs reach the candidates where failures are expected. FairTest is evaluated on three environments and two MARL algorithms, and four baselines are given the same budget. It detects the most fairness failures compared to three baselines with statistical significance and large effect sizes. The failure count exceeds that of the strongest baseline by 221% on average and coverage improves by an average of 23%.
Sep 22, 2026

MATES: Learning Multi-Agent Interactions by Transforming Observations for Frozen Single-Agent Policies

Multi-agent reinforcement learning (MARL) commonly trains decentralized policies from scratch, requiring agents to acquire individual task competence and coordination simultaneously. Yet many multi-agent problems admit a compatible single-agent counterpart in which the underlying task can be learned in isolation. We introduce Multi-Agent Observation Transformation for Existing Single-Agent Policies (MATES), an input-side adaptation framework for tasks whose multi-agent observations preserve the solo-task information while exposing separately identifiable neighbor information. From multi-agent experience, MATES learns a small adapter that maps this observation into the format expected by a frozen single-agent policy, inducing actions suited to the shared environment without updating the single-agent policy itself. MATES leaves the pretrained policy's internal architecture unchanged and retains the objectives and update procedures of the underlying MARL algorithm. We evaluate MATES using both on- and off-policy algorithms on lifelong pathfinding, navigation, and cooperative discovery, spanning discrete and continuous observation and action spaces. Across all evaluated settings, MATES optimizes only 3.5-7.3% as many parameters as full-policy training while consistently outperforming MARL training from scratch. It approaches the performance of full fine-tuning, remains competitive overall with demonstration-based baselines, and retains strong task performance at team sizes not encountered during training. These results provide evidence that, under this observation structure, effective multi-agent behavior can be learned without modifying the policy that encodes individual competence.
Sep 22, 2026

Fully Byzantine-Resilient Multi-Agent Reinforcement Learning

We study distributed Byzantine-resilient actor-critic multi-agent reinforcement learning (AC-MARL), where agents collectively learn policies through local interactions. Existing methods guarantee convergence of the agents' parameters only to a neighborhood of the attack-free limit points, resulting in degraded performance. We propose Fully Resilient AC-MARL (FRAC-MARL), a decentralized method in which each agent leverages redundancy in two-hop messages to identify reliable messages. Under linear parameterizations of the value and team-reward functions and Byzantine edge attacks, where adversarial behavior is confined to the communication layer, we prove that agents' parameters converge almost surely to the same limit points as in the attack-free case over time-varying communication graphs. We introduce a novel topological condition for the convergence of our method, present a systematic method to construct such networks, and prove that this condition can be verified in polynomial time. Finally, we demonstrate our method on cooperative multi-robot formation control tasks.
Sep 20, 2026

VISTA: An Attention-Based Multi-Agent Reinforcement Learning Architecture for Space Situational Awareness Sensor Tasking

The rapid growth of resident space objects is increasing the complexity of space situational awareness sensor tasking, challenging classical optimization methods as they allocate finite, heterogeneous, and distributed sensing resources across ever-larger catalogues. Existing deep reinforcement learning approaches show promise in reduced settings, but fixed-dimensional state and action representations limit their ability to scale to large, dynamic catalogues and distributed sensing networks. We introduce VISTA (Variable-Entity Intelligent Sensor Tasking Architecture), a scalable deep reinforcement learning architecture for persistent uncertainty-driven catalogue maintenance across variable object populations and sensor configurations. VISTA combines physics- and mission-informed top-K retrieval with entity-centric attention, recurrent memory, and pointer-based action decoding, thereby keeping each agent's observation and action spaces independent of catalogue size. We evaluate VISTA across different scenarios, from fixed-size single-sensor benchmarks to large-scale space-based tasking and heterogeneous cooperative sensing. With 30 orbiting targets, VISTA recovers the catalogue 31.2% faster than the fixed-dimensional recurrent baseline. In the large-scale regime, VISTA reduces five-hour uncertainty by 97.5% relative to the strongest classical reference and by 99.3% relative to the recurrent learner. Zero-shot tests up to 20,000 objects reveal near-linear relations between sensing capacity, catalogue size, and recovery horizon. Learned policies also exhibit sensor modality adaptation and generalization to population and initial-uncertainty shifts. Together, these results demonstrate that VISTA provides a scalable framework for adaptive space situational awareness sensor tasking across large, distributed networks of heterogeneous ground- and space-based sensors.
Sep 17, 2026

Mitigating Retaliatory Algorithmic Collusion in Repeated Games

Reinforcement learning agents trained to maximize their own reward in repeated interactions can converge to supra-competitive outcomes resembling explicit collusion, without communication or shared design. Existing mitigation approaches are largely tied to specific economic settings, like two-sided platforms and auctions, leaving open how to design interventions for general repeated games. We address this gap by formalizing the connection between empirical observations from prior work on Q-learning collusion and classical theory of Simple Penal Codes (SPCs). We show any non-trivial SPC induces a quantifiable conditional dependence in agents' policies, detectable via the total variation distance between an agent's action distributions across cooperation and defection histories. Building on this connection, we propose CURB (Collusion Unwinding via Reward shaping and Belief injection), a reward-shaping framework that penalizes this Total Variation (TV) distance signal during Q-learning and is guaranteed to convert any SPC fixed point of the dynamics into a trivial one, thus precluding collusive equilibria sustained by punishment threats. Empirically, CURB substantially reduces collusion by Q-learning agents in both Bertrand and Cournot Competition Repeated Games. We further demonstrate that CURB extends to deep Q-network agents in Bertrand competition, suggesting the mechanism generalizes beyond tabular Q-learning.
Sep 16, 2026

CoRe-MARL: Cooperative Redistribution Under Unknown Dynamics Using Recurrent Multi-Agent Reinforcement Learning

Emergency management assistance programs, such as relief distribution, are essential for delivering necessary supplies to affected communities. However, these programs operate in a decentralized network of local centers that face uncertain local demand and supply dynamics, resulting in inconsistent avail- ability of local services. Redistribution of supplies among these local centers reduces these imbalances, but the centers often make decisions independently, with limited information and disrupted transportation. This study develops CoRe-MARL, a cooperative multi-agent reinforcement learning (MARL) framework, by formulating a decentralized partially observable Markov decision process (Dec-POMDP). We treat each center as an agent that learns a redistribution policy to improve the service in the worst-case region and reduce the service gap across regions while protecting network-wide service. We incorporate a recurrent network that captures evolving supply and demand dynamics without direct observation, while multi-agent proximal policy optimization (MAPPO) enables centralized training and decentralized execution (CTDE). We evaluate the framework in a simulated environment with diverse trajectories, where exact dynamics are not observed by actors and the MAPPO critic. We compare the recurrent MAPPO with the recurrent independent PPO (IPPO) and a local only heuristic, and find that MAPPO reduces the service gap across local centers and enhances service for the worst-served center while maintaining competitive network-wide service. The recurrent MAPPO also shows consistent performance across diverse trajectory patterns, demonstrating its ability to adapt to evolving dynamics. The findings demonstrate the capability of cooperative learning for decentralized redistribution and improving equitable service under uncertain and evolving dynamics.
Sep 16, 2026

DualSQL: Text-to-SQL with Multi-Agent Reinforcement Learning

State-of-the-art Text-to-SQL systems are typically multi-agent pipelines centered around two fundamental tasks: schema linking and SQL generation. However, existing work trains separate models for each task, failing to leverage the synergy between these interrelated tasks. In this work, we propose DualSQL, a new Text-to-SQL system consisting of two agents powered by a single model backbone. The agents share the same model weights and agentic scaffold, enabling joint optimization through a robust multi-agent reinforcement learning (RL) framework. We design three database access tools to facilitate effective multi-step reasoning grounded to interactions with the databases. To improve training and avoid model collapse, we introduce a set of rollout guardrail mechanisms that stabilizes multi-agent RL training, supporting DualSQL to keep improving during training. We also introduce a new SQL correctness metric, robust execution match (REX), to more accurately judge SQL correctness and assign reward signals. Being trained on only 3755 examples, DualSQL-4B achieves an impressive 68.0% execution accuracy on the BIRD development set, matching previous 7B models. DualSQL-8B further improves to 71.1%, outperforming previous state-of-the-art single-model solutions with 32B parameters. These results demonstrate the strength of joint multi-agent reinforcement learning for building high performance Text-to-SQL pipelines.