The concept of meaningful human control has been proposed to address responsibility gaps and mitigate them by establishing conditions that enable a proper attribution of responsibility for humans (e.g., users, designers and developers, manufacturers, legislators). However, the relevant discussions around meaningful human control have so far not resulted in clear requirements for researchers, designers, and engineers. As a result, there is no consensus on how to assess whether a designed AI system is under meaningful human control, making the practical development of AI-based systems that remain under meaningful human control challenging. In this paper, we address the gap between philosophical theory and engineering practice by identifying four actionable properties which AI-based systems must have to be under meaningful human control. First, a system in which humans and AI algorithms interact should have an explicitly defined domain of morally loaded situations within which the system ought to operate. Second, humans and AI agents within the system should have appropriate and mutually compatible representations. Third, responsibility attributed to a human should be commensurate with that human's ability and authority to control the system. Fourth, there should be explicit links between the actions of the AI agents and actions of humans who are aware of their moral responsibility. We argue these four properties are necessary for AI systems under meaningful human control, and provide possible directions to incorporate them into practice. We illustrate these properties with two use cases, automated vehicle and AI-based hiring. We believe these four properties will support practically-minded professionals to take concrete steps toward designing and engineering for AI systems that facilitate meaningful human control and responsibility.

We introduce a voting model with multi-agent ranked delegations. This model generalises liquid democracy in two aspects: first, an agent's delegation can use the votes of multiple other agents to determine their own -- for instance, an agent's vote may correspond to the majority outcome of the votes of a trusted group of agents; second, agents can submit a ranking over multiple delegations, so that a backup delegation can be used when their preferred delegations are involved in cycles. The main focus of this paper is the study of unravelling procedures that transform the delegation ballots received from the agents into a profile of direct votes, from which a winning alternative can then be determined by using a standard voting rule. We propose and study six such unravelling procedures, two based on optimisation and four using a greedy approach. We study both algorithmic and axiomatic properties, as well as related computational complexity problems of our unravelling procedures for different restrictions on the types of ballots that the agents can submit.

The thriving of artificial intelligence (AI) applications is driving the further evolution of wireless networks. It has been envisioned that 6G will be transformative and will revolutionize the evolution of wireless from "connected things" to "connected intelligence". However, state-of-the-art deep learning and big data analytics based AI systems require tremendous computation and communication resources, causing significant latency, energy consumption, network congestion, and privacy leakage in both of the training and inference processes. By embedding model training and inference capabilities into the network edge, edge AI stands out as a disruptive technology for 6G to seamlessly integrate sensing, communication, computation, and intelligence, thereby improving the efficiency, effectiveness, privacy, and security of 6G networks. In this paper, we shall provide our vision for scalable and trustworthy edge AI systems with integrated design of wireless communication strategies and decentralized machine learning models. New design principles of wireless networks, service-driven resource allocation optimization methods, as well as a holistic end-to-end system architecture to support edge AI will be described. Standardization, software and hardware platforms, and application scenarios are also discussed to facilitate the industrialization and commercialization of edge AI systems.

Specifically they present the reward-is-enough hypothesis that "Intelligence, and its associated abilities, can be understood as subserving the maximisation of reward by an agent acting in its environment", and argue in favour of reward maximisation as a pathway to the creation of artificial general intelligence (AGI). While others have criticised this hypothesis and the subsequent claims [44,54,60,64], here we make the argument that Silver et al. have erred in focusing on the maximisation of scalar rewards. The ability to consider multiple conflicting objectives is a critical aspect of both natural and artificial intelligence, and one which will not necessarily arise or be adequately addressed by maximising a scalar reward. In addition, even if the maximisation of a scalar reward is sufficient to support the emergence of AGI, we contend that this approach is undesirable as it greatly increases the likelihood of adverse outcomes resulting from the deployment of that AGI. Therefore, we advocate that a more appropriate model of intelligence should explicitly consider multiple objectives via the use of vector-valued rewards. Our paper starts by confirming that the reward-is-enough hypothesis is indeed referring specifically to scalar rather than vector rewards (Section 2). In Section 3 we then consider limitations of scalar rewards compared to vector rewards, and review the list of intelligent abilities proposed by Silver et al. to determine which of these exhibit multi-objective characteristics. Section 4 identifies multi-objective aspects of natural intelligence (animal and human). Section 5 considers the possibility of vector rewards being internally derived by an agent in response to a global scalar reward.

The cooperative bandit problem is increasingly becoming relevant due to its applications in large-scale decision-making. However, most research for this problem focuses exclusively on the setting with perfect communication, whereas in most real-world distributed settings, communication is often over stochastic networks, with arbitrary corruptions and delays. In this paper, we study cooperative bandit learning under three typical real-world communication scenarios, namely, (a) message-passing over stochastic time-varying networks, (b) instantaneous reward-sharing over a network with random delays, and (c) message-passing with adversarially corrupted rewards, including byzantine communication. For each of these environments, we propose decentralized algorithms that achieve competitive performance, along with near-optimal guarantees on the incurred group regret as well. Furthermore, in the setting with perfect communication, we present an improved delayed-update algorithm that outperforms the existing state-of-the-art on various network topologies. Finally, we present tight network-dependent minimax lower bounds on the group regret. Our proposed algorithms are straightforward to implement and obtain competitive empirical performance.

Recent advances in reinforcement learning (RL) have made it possible to develop sophisticated agents that excel in a wide range of applications. Simulations using such agents can provide valuable information in scenarios that are difficult to scientifically experiment in the real world. In this paper, we examine the play-style characteristics of football RL agents and uncover how strategies may develop during training. The learnt strategies are then compared with those of real football players. We explore what can be learnt from the use of simulated environments by using aggregated statistics and social network analysis (SNA). As a result, we found that (1) there are strong correlations between the competitiveness of an agent and various SNA metrics and (2) aspects of the RL agents play style become similar to real world footballers as the agent becomes more competitive. We discuss further advances that may be necessary to improve our understanding necessary to fully utilise RL for the analysis of football.

Cyber attacks are increasing in volume, frequency, and complexity. In response, the security community is looking toward fully automating cyber defense systems using machine learning. However, so far the resultant effects on the coevolutionary dynamics of attackers and defenders have not been examined. In this whitepaper, we hypothesise that increased automation on both sides will accelerate the coevolutionary cycle, thus begging the question of whether there are any resultant fixed points, and how they are characterised. Working within the threat model of Locked Shields, Europe's largest cyberdefense exercise, we study blackbox adversarial attacks on network classifiers. Given already existing attack capabilities, we question the utility of optimal evasion attack frameworks based on minimal evasion distances. Instead, we suggest a novel reinforcement learning setting that can be used to efficiently generate arbitrary adversarial perturbations. We then argue that attacker-defender fixed points are themselves general-sum games with complex phase transitions, and introduce a temporally extended multi-agent reinforcement learning framework in which the resultant dynamics can be studied. We hypothesise that one plausible fixed point of AI-NIDS may be a scenario where the defense strategy relies heavily on whitelisted feature flow subspaces. Finally, we demonstrate that a continual learning approach is required to study attacker-defender dynamics in temporally extended general-sum games.

Collaborative deep reinforcement learning (CDRL) algorithms in which multiple agents can coordinate over a wireless network is a promising approach to enable future intelligent and autonomous systems that rely on real-time decision-making in complex dynamic environments. Nonetheless, in practical scenarios, CDRL faces many challenges due to the heterogeneity of agents and their learning tasks, different environments, time constraints of the learning, and resource limitations of wireless networks. To address these challenges, in this paper, a novel semantic-aware CDRL method is proposed to enable a group of heterogeneous untrained agents with semantically-linked DRL tasks to collaborate efficiently across a resource-constrained wireless cellular network. To this end, a new heterogeneous federated DRL (HFDRL) algorithm is proposed to select the best subset of semantically relevant DRL agents for collaboration. The proposed approach then jointly optimizes the training loss and wireless bandwidth allocation for the cooperating selected agents in order to train each agent within the time limit of its real-time task. Simulation results show the superior performance of the proposed algorithm compared to state-of-the-art baselines.

The discovery of Behavior Trees (BTs) impacted the field of Artificial Intelligence (AI) in games, by providing flexible and natural representation of non-player characters (NPCs) logic, manageable by game-designers. Nevertheless, increased pressure on ever better NPCs AI-agents forced complexity of handcrafted BTs to became barely-tractable and error-prone. On the other hand, while many just-launched on-line games suffer from player-shortage, the existence of AI with a broad-range of capabilities could increase players retention. Therefore, to handle above challenges, recent trends in the field focused on automatic creation of AI-agents: from deep- and reinforcementlearning techniques to combinatorial (constrained) optimization and evolution of BTs. In this paper, we present a novel approach to semi-automatic construction of AI-agents, that mimic and generalize given human gameplays by adapting and tuning of expert-created BT under a developed similarity metric between source and BT gameplays. To this end, we formulated mixed discrete-continuous optimization problem, in which topological and functional changes of the BT are reflected in numerical variables, and constructed a dedicated hybrid-metaheuristic. The performance of presented approach was verified experimentally in a prototype real-time strategy game. Carried out experiments confirmed efficiency and perspectives of presented approach, which is going to be applied in a commercial game.

Offline reinforcement learning (RL) provides a framework for learning decision-making from offline data and therefore constitutes a promising approach for real-world applications as automated driving. Self-driving vehicles (SDV) learn a policy, which potentially even outperforms the behavior in the sub-optimal data set. Especially in safety-critical applications as automated driving, explainability and transferability are key to success. This motivates the use of model-based offline RL approaches, which leverage planning. However, current state-of-the-art methods often neglect the influence of aleatoric uncertainty arising from the stochastic behavior of multi-agent systems. This work proposes a novel approach for Uncertainty-aware Model-Based Offline REinforcement Learning Leveraging plAnning (UMBRELLA), which solves the prediction, planning, and control problem of the SDV jointly in an interpretable learning-based fashion. A trained action-conditioned stochastic dynamics model captures distinctively different future evolutions of the traffic scene. The analysis provides empirical evidence for the effectiveness of our approach in challenging automated driving simulations and based on a real-world public dataset.