In this paper, we study the problem of robust cooperative multi-agent reinforcement learning (RL) where a large number of cooperative agents with distributed information aim to learn policies in the presence of \emph{stochastic} and \emph{non-stochastic} uncertainties whose distributions are respectively known and unknown. Focusing on policy optimization that accounts for both types of uncertainties, we formulate the problem in a worst-case (minimax) framework, which is is intractable in general. Thus, we focus on the Linear Quadratic setting to derive benchmark solutions. First, since no standard theory exists for this problem due to the distributed information structure, we utilize the Mean-Field Type Game (MFTG) paradigm to establish guarantees on the solution quality in the sense of achieved Nash equilibrium of the MFTG. This in turn allows us to compare the performance against the corresponding original robust multi-agent control problem. Then, we propose a Receding-horizon Gradient Descent Ascent RL algorithm to find the MFTG Nash equilibrium and we prove a non-asymptotic rate of convergence. Finally, we provide numerical experiments to demonstrate the efficacy of our approach relative to a baseline algorithm.

The task that requires an agent to navigate to a given object through only visual observation is called visual object navigation (VON). The main bottlenecks of VON are strategies exploration and prior knowledge exploitation. Traditional strategies exploration ignores the differences of searching and navigating stages, using the same reward in two stages, which reduces navigation performance and training efficiency. Our study enables the agent to explore larger area in searching stage and seek the optimal path in navigating stage, improving the success rate of navigation. Traditional prior knowledge exploitation focused on learning and utilizing object association, which ignored the depth and obstacle information in the environment. This paper uses the RGB and depth information of the training scene to pretrain the feature extractor, which improves navigation efficiency. The obstacle information is memorized by the agent during the navigation, reducing the probability of collision and deadlock. Depth, obstacle and other prior knowledge are concatenated and input into the policy network, and navigation actions are output under the training of two-stage rewards. We evaluated our method on AI2-Thor and RoboTHOR and demonstrated that it significantly outperforms state-of-the-art (SOTA) methods on success rate and navigation efficiency.

However, their computational demands often become a significant barrier as the number of agents and complexity of the simulation increase. Traditional ABM platforms often struggle to fully exploit modern computing resources, hindering the development of large-scale simulations. This paper presents Vahana.jl, a high performance computing open source framework that aims to address these limitations. Building on the formalism of synchronous graph dynamical systems, Vahana.jl is especially well suited for models with a focus on (social) networks. The framework seamlessly supports distribution across multiple compute nodes, enabling simulations that would otherwise be beyond the capabilities of a single machine.

For an autonomous vehicle to plan a path in its environment, it must be able to accurately forecast the trajectory of all dynamic objects in its proximity. While many traditional methods encode observations in the scene to solve this problem, there are few approaches that consider the effect of the ego vehicle's behavior on the future state of the world. In this paper, we introduce VRD, a vectorized world model-inspired approach to the multi-agent motion forecasting problem. Our method combines a traditional open-loop training regime with a novel dreamed closed-loop training pipeline that leverages a kinematic reconstruction task to imagine the trajectory of all agents, conditioned on the action of the ego vehicle. Quantitative and qualitative experiments are conducted on the Argoverse 2 multi-world forecasting evaluation dataset and the intersection drone (inD) dataset to demonstrate the performance of our proposed model. Our model achieves state-of-the-art performance on the single prediction miss rate metric on the Argoverse 2 dataset and performs on par with the leading models for the single prediction displacement metrics.

Understanding the interdependence between autonomous and human-operated vehicles remains an ongoing challenge, with significant implications for the safety and feasibility of autonomous driving.This interdependence arises from inherent interactions among road users.Thus, it is crucial for Autonomous Vehicles (AVs) to understand and analyze the intentions of human-driven vehicles, and to display behavior comprehensible to other traffic participants.To this end, this paper presents GTP-UDRIVE, a unified game-theoretic trajectory planner and decision-maker considering a mixed-traffic environment. Our model considers the intentions of other vehicles in the decision-making process and provides the AV with a human-like trajectory, based on the clothoid interpolation technique.% This study investigates a solver based on Particle Swarm Optimization (PSO) that quickly converges to an optimal decision.Among highly interactive traffic scenarios, the intersection crossing is particularly challenging. Hence, we choose to demonstrate the feasibility and effectiveness of our method in real traffic conditions, using an experimental autonomous vehicle at an unsignalized intersection. Testing results reveal that our approach is suitable for 1) Making decisions and generating trajectories simultaneously. 2) Describing the vehicle's trajectory as a piecewise clothoid and enforcing geometric constraints. 3) Reducing search space dimensionality for the trajectory optimization problem.

Monetary markets serve as established resource allocation mechanisms, typically achieving efficient solutions with limited information. However, they are susceptible to market failures, particularly under the presence of public goods, externalities, or inequality of economic power. Moreover, in many resource allocating contexts, money faces social, ethical, and legal constraints. Consequently, research increasingly explores artificial currencies and non-monetary markets, with Karma emerging as a notable concept. Karma, a non-tradeable, resource-inherent currency for prosumer resources, operates on the principles of contribution and consumption of specific resources. It embodies fairness, near incentive compatibility, Pareto-efficiency, robustness to population heterogeneity, and can incentivize a reduction in resource scarcity. The literature on Karma is scattered across disciplines, varies in scope, and lacks of conceptual clarity and coherence. Thus, this study undertakes a comprehensive review of the Karma mechanism, systematically comparing its resource allocation applications and elucidating overlooked mechanism design elements. Through a systematic mapping study, this review situates Karma within its literature context, offers a structured design parameter framework, and develops a road-map for future research directions.

The study and development of AI agents have been boosted by large language models. AI agents can function as intelligent assistants and complete tasks on behalf of their users with access to tools and the ability to execute commands in their environments, Through studying and experiencing the workflow of typical AI agents, we have raised several concerns regarding their security. These potential vulnerabilities are not addressed by the frameworks used to build the agents, nor by research aimed at improving the agents. In this paper, we identify and describe these vulnerabilities in detail from a system security perspective, emphasizing their causes and severe effects. Furthermore, we introduce defense mechanisms corresponding to each vulnerability with meticulous design and experiments to evaluate their viability. Altogether, this paper contextualizes the security issues in the current development of AI agents and delineates methods to make AI agents safer and more reliable.

Ensuring fair and stable allocation of scarce resources is a fundamental challenge in a wide range of applications. Traditional literature assumes that information regarding agents' preferences, whether available centrally to the designer or held privately by the agents, is known before the allocation process (the mechanism). However, this assumption hinders application in practical settings where agents typically evaluate resources only after receiving or consuming them. Furthermore, such preference information is often noisy and expensive for the central designer to gather from all agents, thus complicating the implementation of traditional mechanisms. Examples of domains where these challenges manifest include applications where geographical and time constraints impede information collection, such as distributing resources to food banks and providing humanitarian aid to disaster areas and war zones [1, 6].

Most prior motion prediction endeavors in autonomous driving have inadequately encoded future scenarios, leading to predictions that may fail to accurately capture the diverse movements of agents (e.g., vehicles or pedestrians). To address this, we propose FutureNet, which explicitly integrates initially predicted trajectories into the future scenario and further encodes these future contexts to enhance subsequent forecasting. Additionally, most previous motion forecasting works have focused on predicting independent futures for each agent. However, safe and smooth autonomous driving requires accurately predicting the diverse future behaviors of numerous surrounding agents jointly in complex dynamic environments. Given that all agents occupy certain potential travel spaces and possess lane driving priority, we propose Lane Occupancy Field (LOF), a new representation with lane semantics for motion forecasting in autonomous driving. LOF can simultaneously capture the joint probability distribution of all road participants' future spatial-temporal positions. Due to the high compatibility between lane occupancy field prediction and trajectory prediction, we propose a novel network with future context encoding for the joint prediction of these two tasks.

The growing presence of artificially intelligent agents in everyday decision-making, from LLM assistants to autonomous vehicles, hints at a future in which conflicts may arise from each agent optimizing individual interests. In general-sum games these conflicts are apparent, where naive Reinforcement Learning agents get stuck in Pareto-suboptimal Nash equilibria. Consequently, opponent shaping has been introduced as a method with success at finding socially beneficial equilibria in social dilemmas. In this work, we introduce Advantage Alignment, a family of algorithms derived from first principles that perform opponent shaping efficiently and intuitively. This is achieved by aligning the advantages of conflicting agents in a given game by increasing the probability of mutually-benefiting actions. We prove that existing opponent shaping methods, including LOLA and LOQA, implicitly perform Advantage Alignment. Compared to these works, Advantage Alignment mathematically simplifies the formulation of opponent shaping and seamlessly works for continuous action domains. We also demonstrate the effectiveness of our algorithm in a wide range of social dilemmas, achieving state of the art results in each case, including a social dilemma version of the Negotiation Game.