No abstract

Traffic light control is one of the main means of controlling road traffic. Improving traffic control is important because it can lead to higher traffic throughput and reduced congestion. This chapter describes multiagent reinforcement learning techniques for automatic optimization of traffic light controllers. Such techniques are attractive because they can automatically discover efficient control strategies for complex tasks, such as traffic control, for which it is hard or impossible to compute optimal solutions directly and hard to develop hand-coded solutions. First the general multi-agent reinforcement learning framework is described that is used to control traffic lights in this work. In this framework, multiple local controllers (agents) are each responsible for the optimization of traffic lights around a single traffic junction, making use of locally perceived traffic state information (sensed cars on the road), a learned probabilistic model of car behavior, and a learned value function which indicates how traffic light decisions affect long-term utility, in terms of the average waiting time of cars. Next, three extensions are described which improve upon the basic framework in various ways: agents (traffic junction controllers) taking into account congestion information from neighboring agents; handling partial observability of traffic states; and coordinating the behavior of multiple agents by coordination graphs and the max-plus algorithm.

Advancements in the AI field unfold tremendous opportunities for society. Simultaneously, it becomes increasingly important to address emerging ramifications. Thereby, the focus is often set on ethical and safe design forestalling unintentional failures. However, cybersecurity-oriented approaches to AI safety additionally consider instantiations of intentional malice -including unethical malevolent AI design. Recently, an analogous emphasis on malicious actors has been expressed regarding security and safety for virtual reality (VR). In this vein, while the intersection of AI and VR (AIVR) offers a wide array of beneficial cross-fertilization possibilities, it is responsible to anticipate future malicious AIVR design from the onset on given the potential socio-psycho-technological impacts. For a simplified illustration, this paper analyzes the conceivable use case of Generative AI (here deepfake techniques) utilized for disinformation in immersive journalism. In our view, defenses against such future AIVR safety risks related to falsehood in immersive settings should be transdisciplinarily conceived from an immersive co-creation stance. As a first step, we motivate a cybersecurity-oriented procedure to generate defenses via immersive design fictions. Overall, there may be no panacea but updatable transdisciplinary tools including AIVR itself could be used to incrementally defend against malicious actors in AIVR.

Recent progress in Artificial Intelligence, sensing and network technology, robotics, and (cloud) computing has enabled the development of intelligent autonomous machine systems. Telling such autonomous systems "what to do" in a responsible way, is a non-trivial task. For intelligent autonomous machines to function in human society and collaborate with humans, we see three challenges ahead affecting meaningful control of autonomous systems. First, autonomous machines are not yet capable of handling failures and unexpected situations. Providing procedures for all possible failures and situations is unfeasible because the state-action space would explode. Machines should therefore become self-aware (self-assessment, self-management) enabling them to handle unexpected situations when they arise. This is a challenge for the computer science community. Second, in order to keep (meaningful) control, humans come into a new role of providing intelligent autonomous machines with objectives or goal functions (including rules, norms, constraints and moral values), specifying the utility of every possible outcome of actions of autonomous machines. Third, in order to be able to collaborate with humans, autonomous systems will require an understanding of (us) humans (i.e., our social, cognitive, affective and physical behaviors) and the ability to engage in partnership interactions (such as explanations of task performances, and the establishment of joint goals and work agreements). These are new challenges for the cognitive ergonomics community. CCS CONCEPTS • Human-centered computing → Interaction design → Interaction design theory, concepts and paradigms;

No abstract

The complex socio-technological debate underlying safetycritical and ethically relevant issues pertaining to AI development and deployment extends across heterogeneous research subfields and involves in part conflicting positions. In this context, it seems expedient to generate a minimalistic joint transdisciplinary basis disambiguating the references to specific subtypes of AI properties and risks for an errorcorrection in the transmission of ideas. In this paper, we introduce a highlevel transdisciplinary system clustering of ethical distinction between antithetical clusters of Type I and Type II systems which extends a cybersecurity-oriented AI safety taxonomy with considerations from psychology. Moreover, we review relevant Type I AI risks, reflect upon possible epistemological origins of hypothetical Type II AI from a cognitive sciences perspective and discuss the related human moral perception. Strikingly, our nuanced transdisciplinary analysis yields the figurative formulation of the so-called AI safety paradox identifying AI control and value alignment as conjugate requirements in AI safety. Against this backdrop, we craft versatile multidisciplinary recommendations with ethical dimensions tailored to Type II AI safety. Overall, we suggest proactive and importantly corrective instead of prohibitive methods as common basis for both Type I and Type II AI safety.

No abstract

This paper introduces a novel approach for abstraction selection in reinforcement learning problems modelled as factored Markov decision processes (MDPs), for which a state is described via a set of state components. In abstraction selection, an agent must choose an abstraction from a set of candidate abstractions, each build up from a different combination of state components.