Multi-Robot System (MRS) has garnered widespread research interest and fostered tremendous interesting applications, especially in cooperative control fields. Yet little light has been shed on the compound ability of formation, monitoring and defence in decentralized large-scale MRS for pursuit avoidance, which puts stringent requirements on the capability of coordination and adaptability. In this paper, we put forward a decentralized Imitation learning based Alternative Multi-Agent Proximal Policy Optimization (IA-MAPPO) algorithm to provide a flexible and communication-economic solution to execute the pursuit avoidance task in well-formed swarm. In particular, a policy-distillation based MAPPO executor is firstly devised to capably accomplish and swiftly switch between multiple formations in a centralized manner. Furthermore, we utilize imitation learning to decentralize the formation controller, so as to reduce the communication overheads and enhance the scalability. Afterwards, alternative training is leveraged to compensate the performance loss incurred by decentralization. The simulation results validate the effectiveness of IA-MAPPO and extensive ablation experiments further show the performance comparable to a centralized solution with significant decrease in communication overheads.

Tax incentives and fiscal bonuses have had a significant impact on the Italian economy over the past decade. In particular, the "Superbonus 110" tax relief in 2020, offering a generous 110% deduction for expenses related to energy efficiency improvements and seismic risk reduction in buildings, has played a pivotal role. However, the surge in construction activities has also brought about an unfortunate increase in fraudulent activities. To address this challenge, our research introduces a practical system for monitoring and managing the entire process of the Superbonus 110 tax credit, from its initiation to redemption. This system leverages artificial intelligence and blockchain technology to streamline tax credit management and incorporates controllers based on a Decentralised Autonomous Organisation architecture, bolstered by a Multi-agent System. The outcome of our work is a system capable of establishing a tokenomics framework that caters to the needs and functionalities of both investors and operators. Moreover, it features a robust control system to prevent inadvertent errors like double spending, overspending, and deceitful practices such as false claims of completed work. The collaborative approach between the Decentralised Autonomous Organisation and the Multi-agent System enhances trust and security levels among participants in a competitive environment where potential fraudsters might attempt to exploit the system. It also enables comprehensive tracking and monitoring of the entire Superbonus process. In the realm of engineering, our project represents an innovative fusion of blockchain technology and Multi-agent Systems, advancing the application of artificial intelligence. This integration guarantees the validation, recording, and execution of transactions with a remarkable level of trust and transparency.

Human immunodeficiency virus (HIV) is a major public health concern in the United States, with about 1.2 million people living with HIV and 35,000 newly infected each year. There are considerable geographical disparities in HIV burden and care access across the U.S. The 2019 Ending the HIV Epidemic (EHE) initiative aims to reduce new infections by 90% by 2030, by improving coverage of diagnoses, treatment, and prevention interventions and prioritizing jurisdictions with high HIV prevalence. Identifying optimal scale-up of intervention combinations will help inform resource allocation. Existing HIV decision analytic models either evaluate specific cities or the overall national population, thus overlooking jurisdictional interactions or differences. In this paper, we propose a multi-agent reinforcement learning (MARL) model, that enables jurisdiction-specific decision analyses but in an environment with cross-jurisdictional epidemiological interactions. In experimental analyses, conducted on jurisdictions within California and Florida, optimal policies from MARL were significantly different than those generated from single-agent RL, highlighting the influence of jurisdictional variations and interactions. By using comprehensive modeling of HIV and formulations of state space, action space, and reward functions, this work helps demonstrate the strengths and applicability of MARL for informing public health policies, and provides a framework for expanding to the national-level to inform the EHE.

Artificial intelligence (AI) systems possess significant potential to drive societal progress. However, their deployment often faces obstacles due to substantial safety concerns. Safe reinforcement learning (SafeRL) emerges as a solution to optimize policies while simultaneously adhering to multiple constraints, thereby addressing the challenge of integrating reinforcement learning in safety-critical scenarios. In this paper, we present an environment suite called Safety-Gymnasium, which encompasses safety-critical tasks in both single and multi-agent scenarios, accepting vector and vision-only input. Additionally, we offer a library of algorithms named Safe Policy Optimization (SafePO), comprising 16 state-of-the-art SafeRL algorithms. This comprehensive library can serve as a validation tool for the research community. By introducing this benchmark, we aim to facilitate the evaluation and comparison of safety performance, thus fostering the development of reinforcement learning for safer, more reliable, and responsible real-world applications. The website of this project can be accessed at https://sites.google.com/view/safety-gymnasium.

Agents often exert influence when interacting with humans and non-human agents. However, the ethical status of such influence is often unclear. In this paper, we present the SHAPE framework, which lists reasons why influence may be unethical. We draw on literature from descriptive and moral philosophy and connect it to machine learning to help guide ethical considerations when developing algorithms with potential influence. Lastly, we explore mechanisms for governing algorithmic systems that influence people, inspired by mechanisms used in journalism, human subject research, and advertising.

Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple dialogue tasks. Solutions to more complex tasks, however, are complicated through logic inconsistencies due to cascading hallucinations caused by naively chaining LLMs. Here we introduce MetaGPT, an innovative meta-programming framework incorporating efficient human workflows into LLM-based multi-agent collaborations. MetaGPT encodes Standardized Operating Procedures (SOPs) into prompt sequences for more streamlined workflows, thus allowing agents with human-like domain expertise to verify intermediate results and reduce errors. MetaGPT utilizes an assembly line paradigm to assign diverse roles to various agents, efficiently breaking down complex tasks into subtasks involving many agents working together. On collaborative software engineering benchmarks, MetaGPT generates more coherent solutions than previous chat-based multi-agent systems. Our project can be found at https://github.com/geekan/MetaGPT

A significant challenge facing researchers in the area of multi-agent reinforcement learning (MARL) pertains to the identification of a library that can offer fast and compatible development for multi-agent tasks and algorithm combinations, while obviating the need to consider compatibility issues. In this paper, we present MARLlib, a library designed to address the aforementioned challenge by leveraging three key mechanisms: 1) a standardized multi-agent environment wrapper, 2) an agent-level algorithm implementation, and 3) a flexible policy mapping strategy. By utilizing these mechanisms, MARLlib can effectively disentangle the intertwined nature of the multi-agent task and the learning process of the algorithm, with the ability to automatically alter the training strategy based on the current task's attributes.

Multi-armed bandits are extensively used to model sequential decision-making, making them ubiquitous in many real-life applications such as online recommender systems and wireless networking. We consider a multi-agent setting where each agent solves their own bandit instance endowed with a different set of arms. Their goal is to minimize their group regret while collaborating via some communication protocol over a given network. Previous literature on this problem only considered arm heterogeneity and networked agents separately. In this work, we introduce a setting that encompasses both features. For this novel setting, we first provide a rigorous regret analysis for a standard flooding protocol combined with the classic UCB policy. Then, to mitigate the issue of high communication costs incurred by flooding in complex networks, we propose a new protocol called Flooding with Absorption (FwA). We provide a theoretical analysis of the resulting regret bound and discuss the advantages of using FwA over flooding. Lastly, we experimentally verify on various scenarios, including dynamic networks, that FwA leads to significantly lower communication costs despite minimal regret performance loss compared to other network protocols.

Predicting future trajectories is critical in autonomous navigation, especially in preventing accidents involving humans, where a predictive agent's ability to anticipate in advance is of utmost importance. Trajectory forecasting models, employed in fields such as robotics, autonomous vehicles, and navigation, face challenges in real-world scenarios, often due to the isolation of model components. To address this, we introduce a novel dataset for end-to-end trajectory forecasting, facilitating the evaluation of models in scenarios involving less-than-ideal preceding modules such as tracking. This dataset, an extension of the JRDB dataset, provides comprehensive data, including the locations of all agents, scene images, and point clouds, all from the robot's perspective. The objective is to predict the future positions of agents relative to the robot using raw sensory input data. It bridges the gap between isolated models and practical applications, promoting a deeper understanding of navigation dynamics. Additionally, we introduce a novel metric for assessing trajectory forecasting models in real-world scenarios where ground-truth identities are inaccessible, addressing issues related to undetected or over-detected agents. Researchers are encouraged to use our benchmark for model evaluation and benchmarking.

The task of vision-and-language navigation in continuous environments (VLN-CE) aims at training an autonomous agent to perform low-level actions to navigate through 3D continuous surroundings using visual observations and language instructions. The significant potential of VLN-CE for mobile robots has been demonstrated across a large number of studies. However, most existing works in VLN-CE focus primarily on transferring the standard discrete vision-and-language navigation (VLN) methods to continuous environments, overlooking the problem of collisions. Such oversight often results in the agent deviating from the planned path or, in severe instances, the agent being trapped in obstacle areas and failing the navigational task. To address the above-mentioned issues, this paper investigates various collision scenarios within VLN-CE and proposes a classification method to predicate the underlying causes of collisions. Furthermore, a new VLN-CE algorithm, named Safe-VLN, is proposed to bolster collision avoidance capabilities including two key components, i.e., a waypoint predictor and a navigator. In particular, the waypoint predictor leverages a simulated 2D LiDAR occupancy mask to prevent the predicted waypoints from being situated in obstacle-ridden areas. The navigator, on the other hand, employs the strategy of `re-selection after collision' to prevent the robot agent from becoming ensnared in a cycle of perpetual collisions. The proposed Safe-VLN is evaluated on the R2R-CE, the results of which demonstrate an enhanced navigational performance and a statistically significant reduction in collision incidences.