The game 2048 has attracted millions of people with its simple yet challenging gameplay, leading to the development of numerous computer players. Most successful computer players for 2048 use evaluation functions trained through temporal difference learning (TD learning) or its variants. While TD learning is highly effective and can improve evaluation functions quickly, the performance of these functions often plateaus after a certain number of timesteps. Therefore, it is important to refine those evaluation functions to further enhance the performance of computer players. In this paper, we extend the conventional TD learning approach and propose two refinement algorithms for 2048. Firstly, we conducted detailed experiments to refine the best open-source neural network, and achieved significant performance improvements, increasing the average score from <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$2.49 \times 10^{5}$</tex-math></inline-formula> to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$3.37 \times 10^{5}$</tex-math></inline-formula> in greedy play (1-ply lookahead) and from <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$4.87 \times 10^{5}$</tex-math></inline-formula> to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$5.45 \times 10^{5}$</tex-math></inline-formula> with 3-ply expectimax search. We also applied our refinement method to the state-of-the-art N-tuple network, improving the average score from <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$5.85\times 10^{5}$</tex-math></inline-formula> to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$6.10\times 10^{5}$</tex-math></inline-formula> with 6-ply expectimax search and the tile-downgrading trick.

Personality traits are essential for understanding human behavior, with applications in many areas such as job screening and team building. Traditional self-assessment methods are prone to biases and often mundane, leading to misleading results. To address these limitations, we propose MindEscape a novel game-based approach using a digital 3D Escape Room, and Artificial Intelligence-driven models, based on the OCEAN Five personality traits (openness, conscientiousness, extraversion, agreeableness, neuroticism). We developed a Multi-Output Regression System (MORS), which is used to make personality assessment to human players based on their gameplay data. As this AI model needs labeled data to be trained on, we developed single- and multi-agent systems that emulate human behaviors using custom reward functions powered by deep-Reinforcement Learning and generate the necessary data to train the system. Preliminary experiments with students from Greece and Italy show strong correlations between game-derived profiles and questionnaire baselines. This methodology offers an engaging, scalable and objective alternative for individual and team personality evaluation, advancing data-driven assessment methods.

Little is known about the interactions between the iceberg profile, which is characterized by high vigor scores, as opposed to low scores in tension, depression, anger, fatigue, and confusion, and performance in League of Legends (LOL). For these reasons, the objectives of the present research were to analyze whether performance was influenced by the presence of the iceberg profile before the start of the game, and to determine the changes produced in the iceberg profile of esports players as a function of the final outcome of the game, the players' performance during the game, and pre-game anxiety and self-confidence. The participants were players in a professional LOL esports team during a SuperLiga Orange spring split. The POMS and CSAI-2 questionnaires were used. Performance was assessed using in-game variables such as game result, favorable and unfavorable plays, and KDA (kills/deaths/assists ratio). The results showed that no changes were found in the performance of the players according to the pre-game iceberg profile. Changes were found in the pre- and post-game iceberg profile, according to the final outcome of the game, and the favorable and unfavorable plays. Furthermore, the psychological variables cognitive and somatic anxiety, and self-confidence, had a relationship with the presence or absence of the iceberg profile. To conclude, the iceberg profile does not seem to influence the performance of esports players, although it is modified by events that occur during the game.

Model-driven game development (MDGD) leverages the concept of model-driven engineering and game development. The focus of MDGD is to automate the game development process by emphasizing a higher level of abstraction, which will make game development faster and easier. In recent years, researchers in the MDGD community have developed several approaches in this domain. The goal of this paper is to survey and classify existing works in MDGD, identify the challenges in this domain, and provide promising future research directions. To achieve this, we conducted a systematic review by selecting 43 articles from a set of 849. The results show that MDE techniques are used to develop games in various genres. 42% of the investigated studies proposed a graphical concrete syntax for game specification and 56% of them used different target environment tools such as Unity Engine. Moreover, our suggestions include taking advantage of tooling environments and focusing on game components rather than a complete game.

Previous works have shown that providing visuo-tactile stimuli synchronously or/and congruent to an artificial and physical body part cause users to perceive the artificial body part as their own. Although this illusion over fake limbs has been extended to immersive virtual reality (VR), the effect of haptic feedback on full body has not been yet examined in depth. This study investigates the effects of visuo-tactile and visuo-motor stimulation on inducing embodiment within VR using a full-body motion capture suit with haptic feedback. Our findings reveal that synchronous and congruent visuo-tactile stimulation significantly enhances the sense of embodiment compared to incongruent visuo-tactile or visuo-motor stimulation alone. Further findings related to heart activity and subjective ratings suggest that incongruent visuo-tactile stimulation or the complete absence of haptic feedback may increase the stress level after the threat event, indicating body disconnection or body disownership. These findings have practical implications for VR system design, particularly in gaming and interactive entertainment. Our results showing the effects of visuo-tactile in addition to the visuo-motor stimuli provide valuable insights for optimizing the sense of embodiment in VR experiences. Ultimately, our research underlines the potential of haptic technologies in creating more engaging and immersive virtual environments.

Artificial intelligence (AI) has enabled agents to master complex video games, from first-person shooters like <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Counter-Strike</i> to real-time strategy games such as <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">StarCraft II</i> and racing games like <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Gran Turismo</i>. While these achievements are notable, applying these AI methods in commercial video game production remains challenging due to computational constraints. In commercial scenarios, the majority of computational resources are allocated to 3D rendering, leaving limited capacity for AI methods, which often demand high computational power, particularly those relying on pixel-based sensors. Moreover, the gaming industry prioritizes creating human-like behavior in AI agents to enhance player experience, unlike academic models that focus on maximizing game performance. This paper introduces a novel methodology for training neural networks via imitation learning to play a complex, commercial-standard, VALORANT-like 2v2 tactical shooter game, requiring only modest CPU hardware during inference. Our approach leverages an innovative, pixel-free perception architecture using a small set of ray-cast sensors, which capture essential spatial information efficiently. These sensors allow AI to perform competently without the computational overhead of traditional methods. Models are trained to mimic human behavior using supervised learning on human trajectory data, resulting in realistic and engaging AI agents. Human evaluation tests confirm that our AI agents provide human-like gameplay experiences while operating efficiently under computational constraints. This offers a significant advancement in AI model development for tactical shooter games and possibly other genres.

The Wave Function Collapse (WFC) algorithm is a widely used tile-based algorithm in procedural content generation, including textures, objects, and scenes. However, the current WFC algorithm and related optimized algorithms based on it lack the ability to generate commercial-scale or infinite content due to constraint conflicts and high time complexity. This paper proposes the Nested WFC (N-WFC) algorithm framework to reduce time complexity. To avoid conflict and backtracking problems, we offer a complete and sub-complete tileset preparation strategy, which requires only a small number of tiles to generate infinite, aperiodic, and deterministic content. We use Mario and Carcassonne as two game examples to describe their application and discuss potential research value. Our contribution addresses WFC's challenge in massive content generation and provides a theoretical basis for implementing concrete games.

In video games, the validation of design specifications throughout the development process poses a major challenge as the project grows in complexity and scale and purely manual testing becomes very costly. This paper proposes a new approach to design validation regression testing based on a reinforcement learning technique guided by tasks expressed in a formal logic specification language (TLTL) and the progress made in completing these tasks. This requires no prior knowledge of machine learning to train testing bots, is naturally interpretable and debuggable, and produces dense reward functions without the need for reward shaping. We investigate the validity of our strategy by comparing it to an imitation baseline in experiments organized around three use cases of typical scenarios in commercial video games on a 3D stealth testing environment created in Unity. For each scenario, we analyze the agents' reactivity to modifications in common assets to accommodate design needs in other sections of the game, and their ability to report unexpected gameplay variations. Our experiments demonstrate the practicality of our approach for training bots to conduct automated regression testing in complex video game settings.

A metagame is a collection of knowledge that goes beyond the rules of a game.\nIn competitive, team-based games like Pok\\'emon or League of Legends, it refers\nto the set of current dominant characters and/or strategies within the player\nbase. Developer changes to the balance of the game can have drastic and\nunforeseen consequences on these sets of meta characters. A framework for\npredicting the impact of balance changes could aid developers in making more\ninformed balance decisions. In this paper we present such a Meta Discovery\nframework, leveraging Reinforcement Learning for automated testing of balance\nchanges. Our results demonstrate the ability to predict the outcome of balance\nchanges in Pok\\'emon Showdown, a collection of competitive Pok\\'emon tiers,\nwith high accuracy.\n