The identity design of artificial agents carries growing ethical, psychological, and cultural weight, as ubiquitous language models and diverse robotic forms are blended into everyday use. However, structured approaches to designing coherent and interpretable artificial identities remain limited. To address urgent challenges in artificial identity design, including harmful stereotypes and deceptive practices, we introduce the Identity Design (ID) Framework and an accompanying research agenda. Drawing on emerging work on artificial identity in human-robot interaction and taking an interdisciplinary perspective, we propose twelve design principles across three levels: individual (recognisability, behavioural consistency, identity continuity, memory, persistent goals), group (membership signalling, social alignment, role clarity), and societal (benevolence, artificiality, social justice, transparency). The research agenda outlines open questions around the operationalisation and measurement of identity, social dynamics, and ethical considerations for identity design. Together, they lay the groundwork for future research and responsible practice in robotic, virtual, and multi-embodied agents.

User performance is crucial in interactive systems, capturing how effectively users engage with task execution. Prospectively predicting performance enables the timely identification of users struggling with task demands. While ocular and cardiac signals are widely used to characterise performance-relevant visual behaviour and physiological activation, their potential for early prediction and for revealing the physiological mechanisms underlying performance differences remains underexplored. We conducted a within-subject experiment in a game environment with naturally unfolding complexity, using early ocular and cardiac signals to predict later performance and to examine physiological and self-reported group differences. Results show that the ocular–cardiac fusion model achieves a balanced accuracy of 0.86, and the ocular-only model shows comparable predictive power. High performers exhibited targeted gaze and adjusted visual sampling, and sustained more stable cardiac activation as demands intensified, with a more positive affective experience. These findings demonstrate the feasibility of cross-session prediction from early physiology, providing interpretable insights into performance variation and facilitating future proactive intervention.

Augmented Reality (AR) head-mounted displays (HMDs) offer potential for more inclusive and immersive exercising and exergaming experiences at home. Previous work found that augmenting home objects can create more engaging exercise experiences and identified various home objects that can be augmented to facilitate different exercises. However, it is unclear how these objects can be augmented to enhance exercising and tailored based on the exercise. We conducted a multi-part study involving a design activity using Snapchat and focus group discussion with 28 participants. We present five themes relating to participants' preferences for the augmentation of home objects for exercising, and identify and discuss key guidelines that designers and researchers should consider when augmenting home objects. Our results provide designers with guidelines and ideas for the augmentation of four different exercises, and advance the foundation for future work developing home-based exergaming through AR HMDs to increase people's physical activity levels.

This study explores how robot embodiment influences human perceptions of robot teammates in virtual reality (VR) environments. In a mixed-design experiment, we simulated an immersive control room where participants enacted teaming with autonomous robots to respond to emergency events. We investigated the effects of robot re-embodiment during VR collaboration, comparing avatar type (machinelike, augmented, humanlike) for different robot types (a drone, vehicle, and humanoid) on perceptions of robot teammates. We found increased anthropomorphism improved perceptions of the robots’ nonverbal expressiveness and bodily-based capabilities but reduced the perceived appearance-based trustworthiness of the robots. Despite their limited non-verbal communication abilities, machinelike embodiments were perceived as more suitable for VR interaction. At the same time, our results suggest that augmented forms offer a compromise, improving the non-verbal communication capabilities of non-anthropomorphic robots with little impact on perceptions of intelligence, trustworthiness, or social abilities. These findings highlight the trade-offs in designing multi-embodied artificial teammates and suggest that alignment between appearance and functionality is critical for effective VR-based human-robot teams.

Videogames are persuasive tools that can direct players’ pro-environmental attitudes. However, there is limited understanding of their impacts on attitudes in a climate-themed context. With a focus on message design and framing, this paper investigated the role and significance of videogames in climate communication. We conducted two parallel within-subjects experiments using two climate-themed games, Beyond Blue (N=36) and Plasticity (N=37), to examine the effects of persuasive game design in directing attitudes. We found that, regardless of message design, both games increased players’ cognitive attitudes after gameplay. We also found that Plasticity’s multi-layered message design (central loss-frame with a potential hopeful ending) increased short-term awareness of the climate-change threat and long-term hope for dealing with the issue, balancing fear and empowerment and emphasising the intricacies of message framing. By demonstrating the efficacy of persuasive design and environmental message framing in gameful interventions using explicit and implicit measures, our paper contributes to the application of interactive technology for effective climate-change communication in the short and long-term. • Videogames can be persuasive tools in climate communication through message framing. • Environmental message framing in games can influence cognitive attitudes. • Subtleties of message framing in videogames can affect the reach of the impact. • Mixed message designs can enhance game-based climate communication outcomes.

Although exercising at home has benefits, it is not always engaging or motivating. Augmented Reality (AR) head-mounted displays (HMDs) offer the potential to make in-home exercising and exergaming more inclusive and immersive, but there is limited research investigating how such systems can be designed. We employed a participatory design approach involving semi-structured interviews to investigate how homes can be augmented to facilitate exercising experiences. We developed 10 recommendations for developing home-based exercising experiences using AR HMDs. Our results further contribute to the existing body of research on the use of AR for exercising, home applications, and everyday objects by presenting the first foundational study investigating the wide range of exercises that can be supported through AR HMDs in home environments and the different ways home elements may support these exercises, and laying the groundwork for future work developing home-based exergaming through AR HMDs to increase people’s physical activity levels.

Videogames are an innovative and promising arena in climate communication, but there is limited understanding of how their design can contribute to this field. Improving this knowledge can help designers create appealing and effective ecogames. In a repeated measures design, we conducted a qualitative interventional study ($\mathrm{N}=34$). In a series of interviews (short-term) and descriptive surveys (long-term), we examined how, and to what extent, a commercial eco-game (Beyond Blue, 2020) can influence participants’ environmental attitudes, biocentric awareness, and eco-motivation. Participants shared their experience of Beyond Blue’s gameplay, as well as their opinions on how to improve it and develop successful eco-games. We found that ecogames can be effective in illustrating and envisioning different ecological setups and constructing a link between people and the environment. Our findings produce design recommendations for eco-games and shed light on how enhancing the interactivity of game mechanics, persuasiveness of the narrative, immersive realism of the animation, and theme-appropriate framing can aid in conveying environmental messages. We highlight choice-driven and customisable gameplay as efficient ways to improve eco-games.

Videogames have the capacity to change people’s attitudes by engaging players with interactive gameplay, persuasive narratives, and immersive simulated realities. We present a framework that targets attitudinal evaluation in game design by describing how game mechanics, narrative, and animation features form player experiences that influence attitudes. To test this framework, we conducted an interventional study (N=36) using a repeated measures design that tested the effects of a climate-themed simulation game, Beyond Blue, on players’ explicit and implicit pro-environmental attitudes in both the short and long term. We also measured the effects of feature-based design (mechanics, narrative, and animation) and elemental design on attitudes. Our results showed that the climate-themed intervention impacted participants’ short-term cognitive attitudes. We also found that Beyond Blue’s overall mechanics and narrative features were the main significant predictors of pro-environmental cognitive attitudes. Challenge design was the only significant element that predicted participants’ cognitive attitudes. Our results demonstrate that climate communication can benefit from a carefully designed theme-oriented videogame as an effective creative tool.

Videogames can be persuasive assets in climate communication. However, there is insufficient knowledge on how to employ specific game design aspects to influence attitudes in the context of climate change. We developed a novel conceptual Climate-Oriented Persuasive Edutainment (C.O.P.E.) model to describe how game design features and elements wrapped in a climate-themed message frame can contribute to pro-environmental attitudes. We evaluated the design decisions in a loss-framed climate-themed videogame (Plasticity) as our case study. In a repeated measures interventional experiment (N=37), we examined the effects of Plasticity on players’ explicit and implicit pro-environmental attitudes in the short and long term. We also assessed participants’ experiences of the attitudinal capacity of three features of game design (mechanics, narrative, animation) and their relevant elements. We found that playing Plasticity influenced participants’ threat perception and cognitive attitudes in the short term. The overall mechanics and narrative features were predictors of participants’ climate threat perception, while the overall animation design predicted pro-environmental cognitive attitude. The storyline was the only element that predicted both threat perception and cognitive attitude. Also, the challenge design predicted threat perception and the exploration design predicted cognitive attitudes. Our work shows that a theme-pertinent, detail-oriented game design can be effective in enhancing climate communication.

Multi-embodied agents can have both physical and virtual bodies, moving between real and virtual environments to meet user needs, embodying robots or virtual agents alike to support extended human-agent relationships. As a design paradigm, multi-embodiment offers potential benefits to improve communication and access to artificial agents, but there are still many unknowns in how to design these kinds of systems. This paper presents the results of a scoping review of the multi-embodiment research, aimed at consolidating the existing evidence and identifying knowledge gaps. Based on our review, we identify key research themes of: multi-embodied systems, identity design, human-agent interaction, environment and context, trust, and information and control. We also identify 16 key research challenges and 12 opportunities for future research.

In 2017, the AlphaZero algorithm achieved superhuman performance in chess, outperforming the then-reigning chess engine Stockfish 8. AlphaZero has since been applied to other variants of chess, such as Crazyhouse, with similarly impressive results. However, limited work has been done on the chess variant Bughouse, which has both cooperative and real-time aspects, as well as a far higher game tree complexity than chess. In this paper, we present HiveMind, a neural network Bughouse engine that focuses on cooperation and decision-making. We trained HiveMind via supervised learning on human Bughouse games. We then used the AlphaZero algorithm by incorporating domain knowledge, using clock times to determine the optimal turn sequence, to perform a tree search over both boards. This two-board search incorporated all aspects of Bughouse, including being time aware and capable of cross-board coordination without heuristics. Finally, we evaluated the strength of HiveMind by playing matches with different time settings against Fairy-Stockfish, the current state-of-the-art alpha-beta Bughouse engine. HiveMind convincingly defeated Fairy-Stockfish achieving a win rate of over 95% with a search time of 2 seconds, showing significantly better scaling.

Fighting games can have barriers to entry as a result of the competency and skill needed to understand the mechanics and objectives of play. One of the key challenges in fighting game design is to teach players how to attain competency. The most common teaching strategy employed in many fighting games is to include a tutorial level. However, there is a lack of research on how fighting game tutorial levels should be designed to support learning for new players. In this paper, we propose design guidelines for video game tutorials, based on the Cognitive Theory of Multimedia Learning and video game design theory. We developed a fighting game tutorial, based on our design guidelines. We evaluated our design against a popular, recent fighting game, Guilty Gear Strive, in a user study with 10 players new to the genre. Our evaluation showed that our design improved on the in-game tutorial, in terms of supporting player learning. We also demonstrated that our design guidelines can provide useful insights into how to provide learning support in fighting game tutorials.

Procedural Content Generation via Machine Learning (PCGML) has been studied to generate terrain maps, but many studies focus on height maps and lack human control. We propose a method based on Generative Adversarial Networks (GANs) to generate multilayer maps of terrain with statistical attributes as inputs to introduce more human control. Since the discriminators used in GANs are difficult to evaluate and lack transparency, we propose attribute loss functions, which work as a supervised approach to evaluate the statistical attributes of generated maps directly using differentiable functions for backpropagation. We tested combinations of two model architectures and different conditional normalisation methods and analysed their characteristics. We found that CGAN architecture with batch normalisation worked well in general, while SPADE block introduced more fragments, and channel-wise normalisation satisfied input conditions better but lost distribution diversity and inter-layer relationships.

The Arcade Learning Environment (ALE) has become an essential benchmark for assessing the performance of reinforcement learning algorithms. However, the computational cost of generating results on the entire 57-game dataset limits ALE’s use and makes the reproducibility of many results infeasible. We propose a novel solution to this problem in the form of a principled methodology for selecting small but representative subsets of environments within a benchmark suite. We applied our method to identify a subset of five ALE games, we call Atari-5, which produces 57-game median score estimates within 10% of their true values. Extending the subset to 10-games recovers 80% of the variance for log-scores for all games within the 57-game set. We show this level of compression is possible due to a high degree of correlation between many of the games in ALE.

Heuristics present a cheap and effective way of evaluating usability. However, in video games, evaluating unique player experiences that are dependent on individual preferences and abilities presents a challenge that goes beyond usability. Video games are more than just functional software, so games heuristics have been adapted to help examine functionality and experience. This paper reports on how papers published in the ACM Digital Library between 2012 and 2022 develop and apply heuristics in video games research. We found that heuristics are often used outside their intended purpose of being used in an expert evaluation. Instead, they are used as survey instruments, interview guides, codes for thematic analysis, and as design guidelines. This research contributes to HCI and video games research by distinguishing the terms design guidelines and design principles from heuristics. We make recommendations for researchers around developing heuristics and conducting video game heuristic evaluations. We propose a method for operationalising heuristics and make recommendations for the implementation of heuristics to improve the quality of video game heuristic reviews.

This paper explores the problem of simultaneously learning a value function and policy in deep actor-critic reinforcement learning models. We find that the common practice of learning these functions jointly is sub-optimal due to an order-of-magnitude difference in noise levels between the two tasks. Instead, we show that learning these tasks independently, but with a constrained distillation phase, significantly improves performance. Furthermore, we find that policy gradient noise levels decrease when using a lower \textit{variance} return estimate. Whereas, value learning noise level decreases with a lower \textit{bias} estimate. Together these insights inform an extension to Proximal Policy Optimization we call \textit{Dual Network Architecture} (DNA), which significantly outperforms its predecessor. DNA also exceeds the performance of the popular Rainbow DQN algorithm on four of the five environments tested, even under more difficult stochastic control settings.

We propose a new research framework by which the nascent discipline of human-AI teaming can be explored within experimental environments in preparation for transferal to real-world contexts. We examine the existing literature and unanswered research questions through the lens of an Agile approach to construct our proposed framework. Our framework aims to provide a structure for understanding the macro features of this research landscape, supporting holistic research into the acceptability of human-AI teaming to human team members and the affordances of AI team members. The framework has the potential to enhance decision-making and performance of hybrid human-AI teams. Further, our framework proposes the application of Agile methodology for research management and knowledge discovery. We propose a transferability pathway for hybrid teaming to be initially tested in a safe environment, such as a real-time strategy video game, with elements of lessons learned that can be transferred to real-world situations.

The potential value of online reviews has led to more and more spam reviews appearing on the web. These spam reviews are widely distributed, harmful, and difficult to identify manually. In this paper, we explore and implement generalised approaches for identifying online deceptive spam game reviews from Steam. We analyse spam game reviews and present and validate some techniques to detect them. In addition, we aim to identify the unique features of game reviews and to create a labelled game review dataset based on different features. We were able to create a labelled dataset that can be used to identify spam game reviews in future research. Our method resulted in 5,021 of the 33,450 unlabelled Steam reviews being labelled as spam reviews, or approximately 15%. This falls within the expected range of 10-20% and maps to the Yelp figures of 14-20% of reviews are spam.

Algorithmic generation of data, known as procedural content generation, is an attractive prospect within the game development industry as a means of creating infinitely fresh and varied content. In this paper, we present an approach to level generation for roguelike dungeon style levels, based on our examination of the suite of existing approaches used in formal research. Our generator aims to create simple dungeon style level layouts that are always playable. We utilise a hybrid technique combining context free grammars to generate a description of levels and a cellular automata inspired process to generate the physical space. The generator proves successful at consistently generating dungeon layouts that maintain completability at all times with sufficient variation, when accounting for the occasional need for corrective actions. We conclude that there is substantial value in hybrid approaches to automated level design and propose a new heuristic by which to assess dungeon style level content.

The purpose of this paper is to draw together theories, ideas, and observations related to rewards, motivation, and play to develop and question our understanding and practice of designing reward-based systems and technology. Our exploration includes reinforcement, rewards, motivational theory, flow, play, games, gamification, and machine learning. We examine the design and psychology of reward-based systems in society and technology, using gamification and machine learning as case studies. We propose that the problems that exist with reward-based systems in our society are also present and pertinent when designing technology. We suggest that motivation, exploration, and play are not just fundamental to human learning and behaviour, but that they could transcend nature into machine learning. Finally, we question the value and potential harm of the reward-based systems that permeate every aspect of our lives and assert the importance of ethics in the design of all systems and technology.

In this paper, we report on a work in progress project that aims to understand affordances and inhibiters of enjoyment in virtual reality (VR) video games. We apply the GameFlow model to review and analyse VR and non-VR versions of the same games to identify differences in enjoyment. Our approach includes conducting expert reviews using the GameFlow model, as well as conducting qualitative analysis on video game reviews, using GameFlow as a conceptual foundation. In this paper, we report our initial findings for the game Superhot. Our ongoing work evaluates a selection of games to map opportunities and pitfalls when designing games for VR.