Umeå University's logo

Until recently the game industry heavily relied on manual playtesting to test the games it produces. Even if the benefits of introducing automated testing are acknowledged, it is rarely done in practice. Some of the main hurdles include the lack of automated testing tools that can target computer games as well as the complexity of automated game plays which are much more difficult to program than typical simple test sequences. This article presents an agent-based testing framework called aplib that comes with a Domain Specific Language (DSL) that allows complex playtests to be programmed more abstractly. A so-called goal structure is used to abstractly formulate a playtest scenario in terms of main goals and their decomposition into subgoals. Scenarios that are not too complicated can be formulated using static goal structures. More complex scenarios may need a test agent that can dynamically adapt its play according to the situation that evolves during the play. To handle such cases, aplib allows dynamic goals to be expressed as well. Invariants and pre-/post-conditions are used to assert the properties that a play is expected to satisfy. They include differential properties that allow constraints on the current state to be related to that of past states. Three case studies are included in the article. The first one aims to evaluate the performance of playtests programmed with aplib. The second shows that the approach can also be combined with other automated testing approaches, in this case reinforcement learning. The third shows the applicability of such playtests in a 3D setup and for non-functional testing.

Modern computer games have become very complex, so they can benefit from automated testing. However, their huge and fine grained interaction space makes them very challenging for automated testing algorithms. Having a model of a system would greatly improve the effectiveness of a testing algorithm. However, manually constructing a model is expensive and time-consuming. This paper proposes an online agent-based search approach to solve common testing tasks for computer games, in particular games that involve elements of world navigation and exploration. On the fly, the approach also constructs a model of the system, which is then exploited to solve the given testing task. The effectiveness of the approach is studied via a case study called Lab Recruits and its simulation of another game called Dungeons and Dragons Online. The study showed that the approach is superior in its ability to complete testing tasks and its completion time compared to evolutionary algorithm, Q-learning and MCTS. This paper extends a previous work presented in ATEST by including evaluation on large game levels, evaluation of the achieved coverage and fault detection and the aforementioned comparison with other algorithms.

Values and context are important in an agent’s decision-making process. Individuals may prioritise values differently, and changing context can also necessitate different considerations. In this paper, we use Schwartz’s theory of basic human values to define ethical values and introduce a preorder to model an agent’s relative preference among those values. We characterise context using this preorder, which can then be used in socio-technical systems as part of the autonomous agents’ deliberation process. We also define the transition between contexts as shifts in value order. To illustrate our approach, we implement this preorder in a domestic water-consumption scenario featuring two towns whose citizens make daily decisions regarding showering, considering visitors, drought rules, and sports activities. Our results demonstrate how our model can effectively represent value orders and integrate them into agents’ decision-making processes. This approach also allows us to characterise contexts, understand how these contexts affect agents’ behaviour, and assess the impact of shifting contexts. We observe that the value order influences the dynamics of context transitions, making some value orders more prone to shift than others.

Automated testing of computer games is a challenging problem, especially when lengthy scenarios have to be tested. Automating such a scenario boils down to finding the right sequence of interactions given an abstract description of the scenario. Recent works have shown that an agent-based approach works well for the purpose, e.g. due to agents' reactivity, hence enabling a test agent to immediately react to game events and changing state. Many games nowadays are multi-player. This opens up an interesting possibility to deploy multiple cooperative test agents to test such a game, for example to speed up the execution of multiple testing tasks. This paper offers a cooperative multi-agent testing approach and a study of its performance based on a case study on a 3D game called Lab Recruits.

Human-AI coevolution, defined as a process in which humans and AI algorithms continuously influence each other, increasingly characterises our society, but is understudied in artificial intelligence and complexity science literature. Recommender systems and assistants play a prominent role in human-AI coevolution, as they permeate many facets of daily life and influence human choices through online platforms. The interaction between users and AI results in a potentially endless feedback loop, wherein users' choices generate data to train AI models, which, in turn, shape subsequent user preferences. This human-AI feedback loop has peculiar characteristics compared to traditional human-machine interaction and gives rise to complex and often “unintended” systemic outcomes. This paper introduces human-AI coevolution as the cornerstone for a new field of study at the intersection between AI and complexity science focused on the theoretical, empirical, and mathematical investigation of the human-AI feedback loop. In doing so, we: (i) outline the pros and cons of existing methodologies and highlight shortcomings and potential ways for capturing feedback loop mechanisms; (ii) propose a reflection at the intersection between complexity science, AI and society; (iii) provide real-world examples for different human-AI ecosystems; and (iv) illustrate challenges to the creation of such a field of study, conceptualising them at increasing levels of abstraction, i.e., scientific, legal and socio-political.

In contemporary society, we live and act within institutions. Institutions are understood here broadly as behavioural regularities in social interaction, which may result from people following formal or informal rules, explicit or tacit norms, or even taken-for-granted ways of acting in society. Understood broadly in this way, as many sociologists, anthropologists, political scientists, and economists do, social institutions are ubiquitous. When we buy and sell, learn and teach, or even simply socialize, our behaviours take place within social institutional frameworks of one kind or another. Despite the obvious implications of institutions for how one should act and live, and the importance accorded them in other human sciences, social psychology's engagement with institutions has been fragmented. In an attempt to orient a coherent approach, this chapter develops a social psychological perspective on institutions, discusses existing relevant psychological research in this perspective, and explores the implications of this perspective for future research.

Multiagent systems bring together agents that represent different users with possibly different concerns. When interacting to make decisions, conflicts occur. A well-known case is with privacy. Agents often need to manage the privacy of content that belong to multiple users, such as sharing group pictures on social media. When agents have different expectations on how the content should be shared, multi-party privacy conflicts can arise. How should we design agents to deal with such conflicts? We have studied an empirical user study to understand the effect of group dynamics in various multi-party privacy settings. Our findings show that as users' beliefs and knowledge about others evolve, privacy expectations shift as well. Inspired by this, we propose computational agents that mimic a human-inspired Theory of Mind (ToM) model to help their users preserve their privacy in multi-party privacy conflicts. The agents can express empathy when others are in need but can also fight for their own privacy. We evaluate our approach in multiagent simulations with varying decision-making strategies. Our results demonstrate that ToM-enabled agents improve privacy preservation for all parties, and even more when their understanding of others is dynamically updated through learning.

This paper reflects on the efforts of the ABM community to model for policy from our perspective as policy developer. Our goal is to enrich the understanding the community of this perspective on the policy processes and draw attention to more opportunities for modelling in the policy process. We make this explicit by introducing the problem cycle as part of the policy process. The problem cycle can be understood as an iterative process that precedes the policy cycle and has its own goals and results. By modelling in the problem cycle modellers can add valuable contributions to the policy process without modelling a policy. We provide three initial tools to modellers to advance their thinking on how to do this. One: a mapping showing the usefulness of the various model(ling) goals for each policy phase. Two: a classification of different types of governments and what they value. Three: an introduction to actionable perspectives as an effective way to present results to policy. We conclude by stressing that it is always important to have conversations with policy people on equal footing to identify how to usefully model for policy without modelling a policy.

Quantitative data seems to be essential when validating social agent-based models. However, data collection can be challenging for explanatory social agent-based simulations due to the inherent complexity of underlying social processes. Despite repeated mentions of validating such ABM’s qualitatively, we observed an absence of explicit approaches. In this paper, we propose the use of qualitative structural validation, combining several validity methods. We will demonstrate its application on our own ABM about identity fusion (van den Hurk et al. in Exploring the Stepwise Process and Consequences of Identity Fusion in Different Groups: An ABM. Conference of the European Social Simulation Association. Springer Nature Switzerland, Cham [17]) and argue how a qualitative approach can create explainable stories, contributing to exploration and explanation of social phenomena.

With Artificial intelligence (AI) development and adoption advancing at an unprecedented pace, policymakers and regulators are encountering both significant challenges and opportunities. The challenges emerge from the disconnect between the fragmented & at times siloed policy & technology landscapes, whilst the opportunities relate to novel insights and capabilities afforded to decision-makers to strengthen the evidence base for sustainable policy. While AI offers transformative potential, it also poses substantial risks, such as biases, inequalities, and threats to privacy and security. In this context, AI policy research has emerged as an essential guide to navigating the complex interplay between technological innovation and societal impact. It ensures that advancements in AI align with ethical, legal, and social priorities. AI policy research provides the evidence base needed to address these challenges, fostering accountability, transparency, fairness, and inclusivity in AI governance. It also helps anticipate future regulatory needs, bridge the gap between stakeholders, and ensure that AI technologies are deployed responsibly and equitably, contributing to sustainable development and the public good.

This roadmap, developed through collaborative discussions at the recent AI Policy Research Summit, reflects a shared vision for advancing research on responsible AI policy and governance. It emphasizes the critical role of policy research inensuring that AI development is guided by robust evidence, ethical considerations, and a commitment to sustainability and inclusivity. By prioritizing transparency, accountability, and the well-being of humans and the planet, this roadmap highlights how research can inform global approaches to AI governance, addressing complex societal needs and ethical challenges. It serves as a guiding framework for stakeholders across academia, industry, government, and civil society to collaborate in generating actionable insights and evidence-based strategies, noting that while evidence-based AI policy often draws on data-driven research, it equally values critical theoretical insights and fundamental rights approaches, ensuring a holistic understanding that extends beyond the purely quantifiable.