Practical uses of Artificial Intelligence (AI) in the real world have demonstrated the importance of embedding moral choices into intelligent agents. They have also highlighted that defining top-down ethical constraints on AI according to any one type of morality is extremely challenging and can pose risks. A bottom-up learning approach may be more appropriate for studying and developing ethical behavior in AI agents. In particular, we believe that an interesting and insightful starting point is the analysis of emergent behavior of Reinforcement Learning (RL) agents that act according to a predefined set of moral rewards in social dilemmas. In this work, we present a systematic analysis of the choices made by intrinsically-motivated RL agents whose rewards are based on moral theories. We aim to design reward structures that are simplified yet representative of a set of key ethical systems. Therefore, we first define moral reward functions that distinguish between consequence- and norm-based agents, between morality based on societal norms or internal virtues, and between single- and mixed-virtue (e.g., multi-objective) methodologies. Then, we evaluate our approach by modeling repeated dyadic interactions between learning moral agents in three iterated social dilemma games (Prisoner's Dilemma, Volunteer's Dilemma and Stag Hunt). We analyze the impact of different types of morality on the emergence of cooperation, defection or exploitation, and the corresponding social outcomes. Finally, we discuss the implications of these findings for the development of moral agents in artificial and mixed human-AI societies.

This paper studies a cooperative multi-agent multi-armed stochastic bandit problem where agents operate asynchronously -- agent pull times and rates are unknown, irregular, and heterogeneous -- and face the same instance of a K-armed bandit problem. Agents can share reward information to speed up the learning process at additional communication costs. We propose ODC, an on-demand communication protocol that tailors the communication of each pair of agents based on their empirical pull times. ODC is efficient when the pull times of agents are highly heterogeneous, and its communication complexity depends on the empirical pull times of agents. ODC is a generic protocol that can be integrated into most cooperative bandit algorithms without degrading their performance. We then incorporate ODC into the natural extensions of UCB and AAE algorithms and propose two communication-efficient cooperative algorithms. Our analysis shows that both algorithms are near-optimal in regret.

The new Bi-Touch system, designed by scientists at the University of Bristol and based at the Bristol Robotics Laboratory, allows robots to carry out manual tasks by sensing what to do from a digital helper. The findings, published in IEEE Robotics and Automation Letters, show how an AI agent interprets its environment through tactile and proprioceptive feedback, and then control the robots' behaviours, enabling precise sensing, gentle interaction, and effective object manipulation to accomplish robotic tasks. This development could revolutionise industries such as fruit picking, domestic service, and eventually recreate touch in artificial limbs. Lead author Yijiong Lin from the Faculty of Engineering, explained: "With our Bi-Touch system, we can easily train AI agents in a virtual world within a couple of hours to achieve bimanual tasks that are tailored towards the touch. And more importantly, we can directly apply these agents from the virtual world to the real world without ...

The Pentagon plans to field thousands of drones and other high-tech military equipment within the next two years as the United States military turns to "autonomous systems" to counter China's numerical edge in terms of personnel and weaponry, a senior defence official said. US Deputy Secretary of Defense Kathleen Hicks told a military technology conference in Washington, DC on Monday that the "imperative to innovate" was crucial at a time of strategic competition with China, a rival who Hick described as being very different to the "relatively slow and lumbering" competitors the US faced during the Cold War. While US forces were engaged in fighting for 20 years in Iraq and Afghanistan, "the PRC [People's Republic of China] worked with focus and determination to build a modern military, carefully crafting it to blunt the operational advantages we've enjoyed for decades", Hicks said in a speech. In a candid address that highlighted Washington's view of the military threat posed by China and its ability to out-scale the US military, Hicks said the US maintained an advantage owing to its ability "to imagine, create and master the future character of warfare". Beijing's main military advantage is "mass: more ships, more missiles, more people", she said.

Commonly adopted in the manufacturing and aerospace sectors, digital twin (DT) platforms are increasingly seen as a promising paradigm to control, monitor, and analyze software-based, "open", communication systems. Notably, DT platforms provide a sandbox in which to test artificial intelligence (AI) solutions for communication systems, potentially reducing the need to collect data and test algorithms in the field, i.e., on the physical twin (PT). A key challenge in the deployment of DT systems is to ensure that virtual control optimization, monitoring, and analysis at the DT are safe and reliable, avoiding incorrect decisions caused by "model exploitation". To address this challenge, this paper presents a general Bayesian framework with the aim of quantifying and accounting for model uncertainty at the DT that is caused by limitations in the amount and quality of data available at the DT from the PT. In the proposed framework, the DT builds a Bayesian model of the communication system, which is leveraged to enable core DT functionalities such as control via multi-agent reinforcement learning (MARL), monitoring of the PT for anomaly detection, prediction, data-collection optimization, and counterfactual analysis. To exemplify the application of the proposed framework, we specifically investigate a case-study system encompassing multiple sensing devices that report to a common receiver. Experimental results validate the effectiveness of the proposed Bayesian framework as compared to standard frequentist model-based solutions.

Autonomous robots that can perform common tasks like driving, surveillance, and chores have the biggest potential for impact due to frequency of usage, and the biggest potential for risk due to direct interaction with humans. These tasks take place in openended environments where humans socially interact and pursue their goals in complex and diverse ways. To operate in such environments, such systems must predict this behaviour, especially when the behavior is unexpected and potentially dangerous. Therefore, we summarize trends in various types of tasks, modeling methods, datasets, and social interaction modules aimed at predicting the future location of dynamic, socially interactive agents. Furthermore, we describe long-tailed learning techniques from classification and regression problems that can be applied to prediction problems. To our knowledge this is the first work that reviews social interaction modeling within prediction, and long-tailed learning techniques within regression and prediction.

Benefiting from the powerful capabilities of large language models (LLMs), agents based on LLMs have shown the potential to address domain-specific tasks and emulate human behaviors. However, the content generated by these agents remains somewhat superficial, owing to their limited domain expertise and the absence of an effective cognitive architecture. To address this, we present the Configurable General Multi-Agent Interaction (CGMI) framework, designed to replicate human interactions in real-world scenarios. Specifically, we propose a tree-structured methodology for the assignment, detection, and maintenance of agent personality. Additionally, we designed a cognitive architecture equipped with a skill library based on the ACT* model, which contains memory, reflection, and planning modules. We have also integrated general agents to augment the virtual environment's realism. Using the CGMI framework, we simulated numerous classroom interactions between teacher and students. The experiments indicate that aspects such as the teaching methodology, curriculum, and student performance closely mirror real classroom settings. We will open source our work.

We present DR-HAI -- a novel argumentation-based framework designed to extend model reconciliation approaches, commonly used in human-aware planning, for enhanced human-AI interaction. By adopting an argumentation-based dialogue paradigm, DR-HAI enables interactive reconciliation to address knowledge discrepancies between an explainer and an explainee. We formally describe the operational semantics of DR-HAI, provide theoretical guarantees, and empirically evaluate its efficacy. Our findings suggest that DR-HAI offers a promising direction for fostering effective human-AI interactions.

Deep reinforcement learning (DRL) has seen remarkable success in the control of single robots. However, applying DRL to robot swarms presents significant challenges. A critical challenge is non-stationarity, which occurs when two or more robots update individual or shared policies concurrently, thereby engaging in an interdependent training process with no guarantees of convergence. Circumventing non-stationarity typically involves training the robots with global information about other agents' states and/or actions. In contrast, in this paper we explore how to remove the need for global information. We pose our problem as a Partially Observable Markov Decision Process, due to the absence of global knowledge on other agents. Using collective transport as a testbed scenario, we study two approaches to multi-agent training. In the first, the robots exchange no messages, and are trained to rely on implicit communication through push-and-pull on the object to transport. In the second approach, we introduce Global State Prediction (GSP), a network trained to forma a belief over the swarm as a whole and predict its future states. We provide a comprehensive study over four well-known deep reinforcement learning algorithms in environments with obstacles, measuring performance as the successful transport of the object to the goal within a desired time-frame. Through an ablation study, we show that including GSP boosts performance and increases robustness when compared with methods that use global knowledge.

We investigate multi-agent reinforcement learning for stochastic games with complex tasks, where the reward functions are non-Markovian. We utilize reward machines to incorporate high-level knowledge of complex tasks. We develop an algorithm called Q-learning with reward machines for stochastic games (QRM-SG), to learn the best-response strategy at Nash equilibrium for each agent. In QRM-SG, we define the Q-function at a Nash equilibrium in augmented state space. The augmented state space integrates the state of the stochastic game and the state of reward machines. Each agent learns the Q-functions of all agents in the system. We prove that Q-functions learned in QRM-SG converge to the Q-functions at a Nash equilibrium if the stage game at each time step during learning has a global optimum point or a saddle point, and the agents update Q-functions based on the best-response strategy at this point. We use the Lemke-Howson method to derive the best-response strategy given current Q-functions. The three case studies show that QRM-SG can learn the best-response strategies effectively. QRM-SG learns the best-response strategies after around 7500 episodes in Case Study I, 1000 episodes in Case Study II, and 1500 episodes in Case Study III, while baseline methods such as Nash Q-learning and MADDPG fail to converge to the Nash equilibrium in all three case studies.