Safe MARL

This study presents Causal Attribution and Responsibility-Guided Optimization (CARGO), a multi-agent reinforcement learning framework for cooperative on-ramp merging in mixed traffic. A shared latent-context posterior and an action-conditioned response model estimate directed behavioral influence, with posterior uncertainty propagated into interaction-edge selection. Complementary attribution mechanisms couple signed influence with marginal team utility for cooperative reward shaping and assign responsibility from positive excess tail risk relative to a safe reference policy. Conditional diffusion generates future responses for action-dependent risk estimation. Responsibility-guided preventive optimization calibrates agent-specific risk-reduction requirements to local capacity within a policy trust region, using reserved safety margins, adaptive requirement scaling, and joint feasibility verification. Theoretical analysis establishes risk monotonicity and sufficient local conditions for non-decreasing environmental return under explicit assumptions. Experiments in highway-env across three traffic densities, together with controlled graph-recovery and attribution studies, support the effectiveness of the framework. Under high-density traffic, CARGO increases the success rate by 66.04% and reduces the crash rate by 56.23% relative to the best evaluated baseline for each metric.

Multi-Agent Reinforcement Learning (MARL) shows promise in coordinating connected and automated vehicles but offers no safety guarantee. Although Control Barrier Functions (CBFs) can add this guarantee, their optimization problem can become infeasible in practice due to control bounds. Moreover, they often overapproximate vehicle and road geometry, which makes them conservative. This paper proposes the Backup-Horizon CBF (BH-CBF), which evaluates safety along a horizon until all vehicles stop. BH-CBF is recursively feasible under control bounds, and it considers the exact vehicle and road geometry. Based on BH-CBF, we derive a fully decentralized safety filter that only needs a single broadcast of vehicle states and routes per step and stays real-time in dense traffic. We use BH-CBF to safeguard a MARL policy over its life cycle: as a reward during pre-training, as a run-time filter at deployment, and as a filter in the training loop that keeps fine-tuning on unseen maps collision-free. In simulations on real-world maps of a roundabout and an intersection, BH-CBF avoids all collisions of unsafe MARL policies and keeps its safety guarantee at every step. Existing filters either collide, lose the guarantee, or fall back to full braking far more often. In recorded roundabout traffic with 1264 human-driven vehicles over 115 km, our safeguarded policies shorten the median travel time by 14% compared with the human drivers, without any collision.

Safe Multi-Agent Reinforcement Learning (SMARL) aims to learn cooperative control policies under prescribed safety constraints. Al- though existing SMARL methods focus on enforcing safety during policy optimization, their vulnerability remains largely unexplored. This paper investigates inference-time observation attacks against SMARL, where an adversary perturbs the observations of a subset of agents, thereby altering the actions produced by their policies. We propose MinMax Attack, an attack framework that jointly selects adversarial target actions for compromised agents while accounting for the Cooperative Resistance of benign agents. We further derive a bound on the induced safety cost and characterize its relation- ship with the Compromised-Agent Budget and the Perturbation Budget. Experiments across multiple safety-critical multi-agent benchmarks and representative state-of-the-art SMARL algorithms show that MinMax Attack induces substantially higher safety costs than existing attack baselines while preserving task reward, thereby reducing its detectability and achieving both attack effectiveness and stealthiness.

Cooperative multi-agent tasks often impose constraints on a shared objective or collective safety. A team level violation cost function can measure this constraint outcome, but does not distinguish which agents' actions most strongly influence that violation. We present SafeDiSTL, a constrained multi-agent reinforcement learning framework that allows for credit assignment even with joint constraint measurements. We use Signal Temporal Logic (STL) robustness to measure episode-level violation through running-maximum cost increments. Smooth full-episode robustness and differentiable dynamics provide action sensitivities, which allocate each cost increment across agents at the same decision time. These sensitivities account for delayed effects when weighting agents' shares of each cost increment. We study the framework in cooperative payload transport, connected navigation, and networked traffic control tasks. SafeDiSTL achieves 1.6-5.1x the safe-success rate in transport, improves navigation safe-success by 11.1%, and delivers 50-68% more throughput in traffic when compared to constrained baselines. Results demonstrate a strong improvement of the learned policy in dealing with shared constraint while retaining the performance of unconstrained policies.

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.

Environments are increasingly populated by multiple robots performing independent tasks with limited prior knowledge of each other. Deploying such multi-agent systems presents significant challenges. Specifically, shifts in deployment states compared to training data can lead to poor policy performance and compromised safety. While safety shields exist to mitigate these risks, they are typically reactive, which degrades performance near unseen obstacles,and centralized, limiting their scalability. To address this, we propose a decentralized framework that integrates predictive shielding with model-based finite horizon Q-learning. This approach allows agents to safely adapt their pre-trained policies during deployment. Furthermore, to mitigate livelocks in symmetric scenarios, we introduce a communication- free protocol for conflict resolution

Multi-agent systems are widely used in safety-critical applications that require coordinated behavior under strict safety constraints. Existing approaches face a fundamental trade-off: learning-based methods achieve strong empirical performance but lack theoretical safety guarantees, while control-theoretic methods enforce safety but often lead to overly conservative and inefficient behaviors. We propose a hierarchical multi-agent reinforcement learning framework that enforces hard safety constraints under mild assumptions at low level via a constraint manifold, while enabling effective coordination through high-level policy learning. Our approach provides theoretical safety guarantees in the multi-agent setting and yields stationary learning dynamics, thereby enabling stable and efficient training. Empirically, our method achieves competitive performance while maintaining nearly perfect safety rates, and generalizes effectively to varying numbers of agents and obstacles.

Language models fine-tuned with reinforcement learning typically optimize for task reward, ignoring multi-agent strategic structure. Because these agents condition on natural language game-state descriptions and emit actions through free-form generation, strategic failure modes -- exploiting weaker opponents, coordinating on harmful equilibria, and externalizing costs are inseparable from the language interface itself. We propose Safe Equilibrium Policy Optimization (\sepo{}), a training objective that augments expected payoff with explicit penalties for exploitability, collusion risk, and externality cost. We implement \sepo{} as a reward signal for Group Relative Policy Optimization (GRPO), applied to Gemma4 E4B-it and Qwen3.5-4B after supervised fine-tuning (SFT). Evaluated across five strategic domains: Iterated Prisoner's Dilemma, repeated auctions, two negotiation variants, and Kuhn Poker. \sepo{} achieves zero exploit-pool advantage in Kuhn Poker for both models, outperforms the base model on safety in four domains, and corrects the over-cooperative behavior introduced by SFT. In negotiation, \sepo{} achieves a positive-safety outcome and only the positive normalized relative advantage of any negotiation configuration. Ablation experiments confirm that per-rollout exploit computation is necessary: a shared constant penalty cancels in GRPO advantage normalization (constant control-variate property), producing zero gradient. To support further research in strategic safety for agents, we release our code and SFT datasets.

As Deep Neural Network (DNN) inference becomes increasingly prevalent on edge and mobile platforms, critical challenges emerge in privacy protection, resource constraints, and dynamic model deployment. This paper proposes a privacy-aware collaborative inference framework, in which adaptive model partitioning is performed across edge devices and servers. To jointly optimize inference delay, energy consumption, and privacy cost under dynamic service demands and resource constraints, we formulate the joint problem as a Constrained Markov Decision Process (CMDP) that integrates model deployment, user-server association, model partitioning, and resource allocation. We propose a Hierarchical Constrained Multi-Agent Proximal Policy Optimization with Lagrangian relaxation (HC-MAPPO-L) algorithm, a safe reinforcement learning-based framework that enhances Multi-Agent Proximal Policy Optimization (MAPPO) with adaptive Lagrangian dual updates to enforce long-term delay constraints. To ensure tractability while maintaining coordination, we decompose the CMDP into three hierarchically structured policy layers: an auto-regressive based model deployment policy, a Lagrangian-enhanced user association and model partitioning policy, and an attention-based resource allocation policy. Extensive experimental results demonstrate that HC-MAPPO-L consistently satisfies stringent delay constraints while achieving a superior balance among energy consumption and privacy cost, outperforming representative baseline algorithms across varying problem scales and resource configurations.