The article reviews significant advances in networked signal and information processing, which have enabled in the last 25 years extending decision making and inference, optimization, control, and learning to the increasingly ubiquitous environments of distributed agents. As these interacting agents cooperate, new collective behaviors emerge from local decisions and actions. Moreover, and significantly, theory and applications show that networked agents, through cooperation and sharing, are able to match the performance of cloud or federated solutions, while offering the potential for improved privacy, increasing resilience, and saving resources.

Causal reasoning and game-theoretic reasoning are fundamental topics in artificial intelligence, among many other disciplines: this paper is concerned with their intersection. Despite their importance, a formal framework that supports both these forms of reasoning has, until now, been lacking. We offer a solution in the form of (structural) causal games, which can be seen as extending Pearl's causal hierarchy to the game-theoretic domain, or as extending Koller and Milch's multi-agent influence diagrams to the causal domain. We then consider three key questions: i) How can the (causal) dependencies in games - either between variables, or between strategies - be modelled in a uniform, principled manner? ii) How may causal queries be computed in causal games, and what assumptions does this require? iii) How do causal games compare to existing formalisms? To address question i), we introduce mechanised games, which encode dependencies between agents' decision rules and the distributions governing the game. In response to question ii), we present definitions of predictions, interventions, and counterfactuals, and discuss the assumptions required for each. Regarding question iii), we describe correspondences between causal games and other formalisms, and explain how causal games can be used to answer queries that other causal or game-theoretic models do not support. Finally, we highlight possible applications of causal games, aided by an extensive open-source Python library.

In this paper, we develop and present a novel strategy for safe coordination of a large-scale multi-agent team with ``\textit{local deformation}" capabilities. Multi-agent coordination is defined by our proposed method as a multi-layer deformation problem specified as a Deep Neural Network (DNN) optimization problem. The proposed DNN consists of $p$ hidden layers, each of which contains artificial neurons representing unique agents. Furthermore, based on the desired positions of the agents of hidden layer $k$ ($k=1,\cdots,p-1$), the desired deformation of the agents of hidden layer $k + 1$ is planned. In contrast to the available neural network learning problems, our proposed neural network optimization receives time-invariant reference positions of the boundary agents as inputs and trains the weights based on the desired trajectory of the agent team configuration, where the weights are constrained by certain lower and upper bounds to ensure inter-agent collision avoidance. We simulate and provide the results of a large-scale quadcopter team coordination tracking a desired elliptical trajectory to validate the proposed approach.

Recent studies in Vision-and-Language Navigation (VLN) train RL agents to execute natural-language navigation instructions in photorealistic environments, as a step towards robots that can follow human instructions. However, given the scarcity of human instruction data and limited diversity in the training environments, these agents still struggle with complex language grounding and spatial language understanding. Pretraining on large text and image-text datasets from the web has been extensively explored but the improvements are limited. We investigate large-scale augmentation with synthetic instructions. We take 500+ indoor environments captured in densely-sampled 360 degree panoramas, construct navigation trajectories through these panoramas, and generate a visually-grounded instruction for each trajectory using Marky, a high-quality multilingual navigation instruction generator. We also synthesize image observations from novel viewpoints using an image-to-image GAN. The resulting dataset of 4.2M instruction-trajectory pairs is two orders of magnitude larger than existing human-annotated datasets, and contains a wider variety of environments and viewpoints. To efficiently leverage data at this scale, we train a simple transformer agent with imitation learning. On the challenging RxR dataset, our approach outperforms all existing RL agents, improving the state-of-the-art NDTW from 71.1 to 79.1 in seen environments, and from 64.6 to 66.8 in unseen test environments. Our work points to a new path to improving instruction-following agents, emphasizing large-scale imitation learning and the development of synthetic instruction generation capabilities.

Average consensus is essential for multi-agent systems to achieve specific functions and is widely used in network control, information fusion, etc. In conventional average consensus algorithms, all agents reach an agreement by individual calculations and sharing information with their respective neighbors. Nevertheless, the information interactions that occur in the communication network may make privacy information be revealed. In this paper, we develop a new privacy-preserving average consensus method for unbalanced digraphs. Specifically, we ensure privacy preservation by carefully embedding randomness in mixing weights to confuse communications and introducing an extra auxiliary parameter to mask the state-updated rule in initial several iterations. In parallel, we exploit the intrinsic robustness of consensus dynamics to guarantee that the average consensus is precisely achieved. Theoretical results demonstrate that the designed algorithms can converge linearly to the exact average consensus value and can guarantee privacy preservation of agents against both honest-but-curious and eavesdropping attacks. The designed algorithms are fundamentally different compared to differential privacy based algorithms that enable privacy preservation via sacrificing consensus performance. Finally, numerical experiments validate the correctness of the theoretical findings.

An unmanned surface vehicle (USV) can perform complex missions by continuously observing the state of its surroundings and taking action toward a goal. A SWARM of USVs working together can complete missions faster, and more effectively than a single USV alone. In this paper, we propose an autonomous communication model for a swarm of USVs. The goal of this system is to implement a software system using Robot Operating System (ROS) and Gazebo. With the main objective of coordinated task completion, the Markov decision process (MDP) provides a base to formulate a task decision problem to achieve efficient localization and tracking in a highly dynamic water environment. To coordinate multiple USVs performing real-time target tracking, we propose an enhanced multi-agent reinforcement learning approach. Our proposed scheme uses MA-DDPG, or Multi-Agent Deep Deterministic Policy Gradient, an extension of the Deep Deterministic Policy Gradients (DDPG) algorithm that allows for decentralized control of multiple agents in a cooperative environment. MA-DDPG's decentralised control allows each and every agent to make decisions based on its own observations and objectives, which can lead to superior gross performance and improved stability. Additionally, it provides communication and coordination among agents through the use of collective readings and rewards.

Mean field games (MFGs) provide a mathematically tractable framework for modelling large-scale multi-agent systems by leveraging mean field theory to simplify interactions among agents. It enables applying inverse reinforcement learning (IRL) to predict behaviours of large populations by recovering reward signals from demonstrated behaviours. However, existing IRL methods for MFGs are powerless to reason about uncertainties in demonstrated behaviours of individual agents. This paper proposes a novel framework, Mean-Field Adversarial IRL (MF-AIRL), which is capable of tackling uncertainties in demonstrations. We build MF-AIRL upon maximum entropy IRL and a new equilibrium concept. We evaluate our approach on simulated tasks with imperfect demonstrations. Experimental results demonstrate the superiority of MF-AIRL over existing methods in reward recovery.

This paper analyzes cooperative data-sharing between competitors vying to predict a consumer's tastes. We design optimal data-sharing schemes both for when they compete only with each other, and for when they additionally compete with an Amazon – a company with more, better data. We show that simple schemes – threshold rules that probabilistically induce either full data-sharing between competitors, or the full transfer of data from one competitor to another – are either optimal or approximately optimal, depending on properties of the information structure. We also provide conditions under which firms share more data when they face stronger outside competition, and describe situations in which this conclusion is reversed.

In this paper, we investigate a distributed aggregative optimization problem in a network, where each agent has its own local cost function which depends not only on the local state variable but also on an aggregated function of state variables from all agents. To accelerate the optimization process, we combine heavy ball and Nesterov's accelerated methods with distributed aggregative gradient tracking, and propose two novel algorithms named DAGT-HB and DAGT-NES for solving the distributed aggregative optimization problem. We analyse that the DAGT-HB and DAGT-NES algorithms can converge to an optimal solution at a global $\mathbf{R}-$linear convergence rate when the objective function is smooth and strongly convex, and when the parameters (e.g., step size and momentum coefficients) are selected within certain ranges. A numerical experiment on the optimal placement problem is given to verify the effectiveness and superiority of our proposed algorithms.

Cooperative multi-agent reinforcement learning (MARL) requires agents to explore to learn to cooperate. Existing value-based MARL algorithms commonly rely on random exploration, such as $\epsilon$-greedy, which is inefficient in discovering multi-agent cooperation. Additionally, the environment in MARL appears non-stationary to any individual agent due to the simultaneous training of other agents, leading to highly variant and thus unstable optimisation signals. In this work, we propose ensemble value functions for multi-agent exploration (EMAX), a general framework to extend any value-based MARL algorithm. EMAX trains ensembles of value functions for each agent to address the key challenges of exploration and non-stationarity: (1) The uncertainty of value estimates across the ensemble is used in a UCB policy to guide the exploration of agents to parts of the environment which require cooperation. (2) Average value estimates across the ensemble serve as target values. These targets exhibit lower variance compared to commonly applied target networks and we show that they lead to more stable gradients during the optimisation. We instantiate three value-based MARL algorithms with EMAX, independent DQN, VDN and QMIX, and evaluate them in 21 tasks across four environments. Using ensembles of five value functions, EMAX improves sample efficiency and final evaluation returns of these algorithms by 53%, 36%, and 498%, respectively, averaged all 21 tasks.