Realistic traffic simulation is crucial for developing self-driving software in a safe and scalable manner prior to real-world deployment. Typically, imitation learning (IL) is used to learn human-like traffic agents directly from real-world observations collected offline, but without explicit specification of traffic rules, agents trained from IL alone frequently display unrealistic infractions like collisions and driving off the road. This problem is exacerbated in out-of-distribution and long-tail scenarios. On the other hand, reinforcement learning (RL) can train traffic agents to avoid infractions, but using RL alone results in unhuman-like driving behaviors. We propose Reinforcing Traffic Rules (RTR), a holistic closed-loop learning objective to match expert demonstrations under a traffic compliance constraint, which naturally gives rise to a joint IL + RL approach, obtaining the best of both worlds. Our method learns in closed-loop simulations of both nominal scenarios from real-world datasets as well as procedurally generated long-tail scenarios. Our experiments show that RTR learns more realistic and generalizable traffic simulation policies, achieving significantly better tradeoffs between human-like driving and traffic compliance in both nominal and long-tail scenarios. Moreover, when used as a data generation tool for training prediction models, our learned traffic policy leads to considerably improved downstream prediction metrics compared to baseline traffic agents. For more information, visit the project website: https://waabi.ai/rtr

Open multi-agent systems (MAS) are composed of agents under different organisational control, and whose internal goals and mental states cannot be observed. In such systems, agents often have differing capabilities, and must rely on each other when pursuing their goals, making task delegation commonplace. This delegation occurs when one agent (the delegator) requests that another (the delegatee), execute a task. A fundamental problem faced by the delegator involves selecting the most appropriate delegatee to whom the task should be delegated, and a significant body of work centred around trust and reputation systems has examined how such a delegation decision should take place [6, 12, 13]. At their heart, trust and reputation systems associate a rating with each potential delegatee, and select who to delegate a task to based on this rating. Following task execution, the rating is updated based on how well the task was completed. Different systems compute the ratings differently, for example incorporating indirect information from other agents in the system [8, 14], or utilising social and cognitive concepts as part of the computation process [4]. Trust and reputation systems can also differ in the way they select a delegatee, for example by using the rating to weigh the likelihood of selection. While trust and reputation systems seek to satisfy many properties including resistance to different types of attacks by malicious agents [7], at their heart, they balance the exploration of delegatee behaviour with the exploitation of high quality delagatees.

These applications have high, ever-growing requirements in terms of security, reliability and performance. Currently, the development of these applications is heavily dependent on cloud, the abundant resources of which are a necessity for the computationally intensive Artificial Intelligence (AI) methods. However, cloud-native processing requires transmitting data between the end users and the cloud, which increases the latency, burdens the core network and raises privacy concerns. Hence, several computing paradigms, such as edge and fog computing, Multi-access Edge Computing (MEC) and cloudlets (Ren et al. (2020)), have emerged to bring the computing and storage resources from the cloud to the edge, closer to the end users. Even though these paradigms have differences in their architectural considerations and driving forces, they all have the same essence: placing and using computational resources between the end user and the distant cloud in order to reduce latency and energy consumption, as well as increase security and privacy by keeping the application data local. Bringing the intelligent applications onto the edge between the end users and the cloud is not a simple task. Traditional AI is inherently centralized and resource consuming, while the edge is inherently distributed and limited in resources. Further, the edge nodes are highly heterogeneous in terms of their capabilities, while the edge environment as a whole is characterized by intermittent connectivity, distributed and non-IID data, as well as geographically distributed, opportunistic computing resources (Kokkonen et al. (2022)). Research on developing and adapting AI methods to the edge environment has been coined as AI on Edge (Lovén et al. (2019); Deng et al. (2020)), which is an active research area with an ample amount of research (Deng et al. (2020); Xu et al. (2021); Park et al. (2021)).

The potential of digital twin technology is yet to be fully realized due to its diversity and untapped potential. Digital twins enable systems' analysis, design, optimization, and evolution to be performed digitally or in conjunction with a cyber-physical approach to improve speed, accuracy, and efficiency over traditional engineering methods. Industry 4.0, factories of the future, and digital twins continue to benefit from the technology and provide enhanced efficiency within existing systems. Due to the lack of information and security standards associated with the transition to cyber digitization, cybercriminals have been able to take advantage of the situation. Access to a digital twin of a product or service is equivalent to threatening the entire collection. There is a robust interaction between digital twins and artificial intelligence tools, which leads to strong interaction between these technologies, so it can be used to improve the cybersecurity of these digital platforms based on their integration with these technologies. This study aims to investigate the role of artificial intelligence in providing cybersecurity for digital twin versions of various industries, as well as the risks associated with these versions. In addition, this research serves as a road map for researchers and others interested in cybersecurity and digital security.

The construction industry has been notoriously slow to adopt new technology and embrace automation. This has resulted in lower efficiency and productivity compared to other industries where automation has been widely adopted. However, recent advancements in robotics and artificial intelligence offer a potential solution to this problem. In this study, a methodology is proposed to integrate multi-robotic systems in construction projects with the aim of increasing efficiency and productivity. The proposed approach involves the use of multiple robot and human agents working collaboratively to complete a construction task. The methodology was tested through a case study that involved 3D digitization of a small, occluded space using two robots and one human agent. The results show that integrating multi-agent robotic systems in construction can effectively overcome challenges and complete tasks efficiently. The implications of this study suggest that multi-agent robotic systems could revolutionize the industry.

We study the game modification problem, where a benevolent game designer or a malevolent adversary modifies the reward function of a zero-sum Markov game so that a target deterministic or stochastic policy profile becomes the unique Markov perfect Nash equilibrium and has a value within a target range, in a way that minimizes the modification cost. We characterize the set of policy profiles that can be installed as the unique equilibrium of some game, and establish sufficient and necessary conditions for successful installation. We propose an efficient algorithm, which solves a convex optimization problem with linear constraints and then performs random perturbation, to obtain a modification plan with a near-optimal cost.

A lot of recent machine learning research papers have "Open-ended learning" in their title. But very few of them attempt to define what they mean when using the term. Even worse, when looking more closely there seems to be no consensus on what distinguishes open-ended learning from related concepts such as continual learning, lifelong learning or autotelic learning. In this paper, we contribute to fixing this situation. After illustrating the genealogy of the concept and more recent perspectives about what it truly means, we outline that open-ended learning is generally conceived as a composite notion encompassing a set of diverse properties. In contrast with these previous approaches, we propose to isolate a key elementary property of open-ended processes, which is to always produce novel elements from time to time over an infinite horizon. From there, we build the notion of open-ended learning problems and focus in particular on the subset of open-ended goal-conditioned reinforcement learning problems, as this framework facilitates the definition of learning a growing repertoire of skills. Finally, we highlight the work that remains to be performed to fill the gap between our elementary definition and the more involved notions of open-ended learning that developmental AI researchers may have in mind.

Hamilton-Jacobi-Isaacs (HJI) PDEs are the governing equations for the two-player general-sum games. Unlike Reinforcement Learning (RL) methods, which are data-intensive methods for learning value function, learning HJ PDEs provide a guaranteed convergence to the Nash Equilibrium value of the game when it exists. However, a caveat is that solving HJ PDEs becomes intractable when the state dimension increases. To circumvent the curse of dimensionality (CoD), physics-informed machine learning methods with supervision can be used and have been shown to be effective in generating equilibrial policies in two-player general-sum games. In this work, we extend the existing work on agent-level two-player games to a two-player swarm-level game, where two sub-swarms play a general-sum game. We consider the \textit{Kolmogorov forward equation} as the dynamic model for the evolution of the densities of the swarms. Results show that policies generated from the physics-informed neural network (PINN) result in a higher payoff than a Nash Double Deep Q-Network (Nash DDQN) agent and have comparable performance with numerical solvers.

The rapid advancement of chat-based language models has led to remarkable progress in complex task-solving. However, their success heavily relies on human input to guide the conversation, which can be challenging and time-consuming. This paper explores the potential of building scalable techniques to facilitate autonomous cooperation among communicative agents, and provides insight into their "cognitive" processes. To address the challenges of achieving autonomous cooperation, we propose a novel communicative agent framework named role-playing. Our approach involves using inception prompting to guide chat agents toward task completion while maintaining consistency with human intentions. We showcase how role-playing can be used to generate conversational data for studying the behaviors and capabilities of a society of agents, providing a valuable resource for investigating conversational language models. In particular, we conduct comprehensive studies on instruction-following cooperation in multi-agent settings. Our contributions include introducing a novel communicative agent framework, offering a scalable approach for studying the cooperative behaviors and capabilities of multi-agent systems, and open-sourcing our library to support research on communicative agents and beyond: https://github.com/camel-ai/camel.

This paper investigates how interacting agents arrive to a consensus or a polarized state. We study the opinion formation process under the effect of a global steering mechanism (GSM), which aggregates the opinion-driven stochastic agent states at the network level and feeds back to them a form of global information. We also propose a new two-layer agent-based opinion formation model, called GSM-DeGroot, that captures the coupled dynamics between agent-to-agent local interactions and the GSM's steering effect. This way, agents are subject to the effects of a DeGroot-like local opinion propagation, as well as to a wide variety of possible aggregated information that can affect their opinions, such as trending news feeds, press coverage, polls, elections, etc. Contrary to the standard DeGroot model, our model allows polarization to emerge by letting agents react to the global information in a stubborn differential way. Moreover, the introduced stochastic agent states produce event stream dynamics that can fit to real event data. We explore numerically the model dynamics to find regimes of qualitatively different behavior. We also challenge our model by fitting it to the dynamics of real topics that attracted the public attention and were recorded on Twitter. Our experiments show that the proposed model holds explanatory power, as it evidently captures real opinion formation dynamics via a relatively small set of interpretable parameters.