Rongyang Li;Jianguo Ding;Huansheng Ning;Lingfeng Mao
Biosignal sequence real-time prediction (BSRP) is essential for predicting the future emotional experience of game users. However, BSRP for game users faces challenges, including poor real-time performance and limited feature fusion dimensions. To address these issues, we proposed a method for BSRP based on the features fusion of local–global and time–frequency domain (LGTF) for game users, which integrates real-time capabilities with multidimensional features fusion. Specifically, LGTF meets real-time requirements and achieves the features fusion of local–global (LG) through multichannel synchronized adaptive convolution. In addition, LGTF implements the features fusion of interband and intraband in the frequency domain and the features fusion of time–frequency (TF) domain by incorporating the self-attention mechanism and Fourier Transform. Furthermore, we conducted comprehensive validation experiments on LGTF using the public dataset. The results indicate that: first, in the comparison study, LGTF outperformed other methods, achieving the lowest average mean squared error (MSE) and mean absolute error values across different prediction lengths of 0.61 and 0.47, respectively. Second, ablation studies revealed that the addition of TF domain feature fusion and LG feature fusion both have the positive effect on the prediction performance, reducing the average MSE by 0.11 and 0.09, respectively. Third, generalization study shows that LGTF exhibits stable performance and generalization across different subjects and shows performance advantages in specific game scenarios. Fourth, time performance analysis suggests LGTF has the real-time performance. Finally, case study demonstrates that LGTF is practical for predicting game users' future emotions and enhancing their emotional experiences.
{"title":"Biosignal Sequence Real-Time Prediction for Game Users Based on Features Fusion of Local–Global and Time–Frequency Domain","authors":"Rongyang Li;Jianguo Ding;Huansheng Ning;Lingfeng Mao","doi":"10.1109/TG.2025.3550779","DOIUrl":"https://doi.org/10.1109/TG.2025.3550779","url":null,"abstract":"Biosignal sequence real-time prediction (BSRP) is essential for predicting the future emotional experience of game users. However, BSRP for game users faces challenges, including poor real-time performance and limited feature fusion dimensions. To address these issues, we proposed a method for BSRP based on the features fusion of local–global and time–frequency domain (LGTF) for game users, which integrates real-time capabilities with multidimensional features fusion. Specifically, LGTF meets real-time requirements and achieves the features fusion of local–global (LG) through multichannel synchronized adaptive convolution. In addition, LGTF implements the features fusion of interband and intraband in the frequency domain and the features fusion of time–frequency (TF) domain by incorporating the self-attention mechanism and Fourier Transform. Furthermore, we conducted comprehensive validation experiments on LGTF using the public dataset. The results indicate that: first, in the comparison study, LGTF outperformed other methods, achieving the lowest average mean squared error (MSE) and mean absolute error values across different prediction lengths of 0.61 and 0.47, respectively. Second, ablation studies revealed that the addition of TF domain feature fusion and LG feature fusion both have the positive effect on the prediction performance, reducing the average MSE by 0.11 and 0.09, respectively. Third, generalization study shows that LGTF exhibits stable performance and generalization across different subjects and shows performance advantages in specific game scenarios. Fourth, time performance analysis suggests LGTF has the real-time performance. Finally, case study demonstrates that LGTF is practical for predicting game users' future emotions and enhancing their emotional experiences.","PeriodicalId":55977,"journal":{"name":"IEEE Transactions on Games","volume":"17 3","pages":"797-812"},"PeriodicalIF":2.8,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145073273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Games are widely used as research environments for multiagent reinforcement learning (MARL), but they pose three significant challenges: limited customization, high computational demands, and oversimplification. To address these issues, we introduce the first publicly available map editor for the popular mobile game Honor of Kings and design a lightweight environment, Mini Honor of Kings (Mini HoK), for researchers to conduct experiments. Mini HoK is highly efficient, allowing experiments to be run on personal PCs or laptops while still presenting sufficient challenges for existing MARL algorithms. We have tested our environment on common MARL algorithms and demonstrated that these algorithms have yet to surpass the performance of rule based policies, indicating that current MARL methods are not able to solve this environment. This facilitates the dissemination and advancement of MARL methods within the research community. In addition, we hope that more researchers will leverage the Honor of Kings map editor to develop innovative and scientifically valuable new maps.
{"title":"Mini Honor of Kings: A Lightweight Environment for Multiagent Reinforcement Learning","authors":"Lin Liu;Jian Zhao;Cheng Hu;Zhengtao Cao;Youpeng Zhao;Zhenbin Ye;Meng Meng;Wenjun Wang;Zhaofeng He;Houqiang Li;Xia Lin;Lanxiao Huang","doi":"10.1109/TG.2025.3546252","DOIUrl":"https://doi.org/10.1109/TG.2025.3546252","url":null,"abstract":"Games are widely used as research environments for multiagent reinforcement learning (MARL), but they pose three significant challenges: limited customization, high computational demands, and oversimplification. To address these issues, we introduce the first publicly available map editor for the popular mobile game <italic>Honor of Kings</i> and design a lightweight environment, <italic>Mini Honor of Kings</i> (Mini HoK), for researchers to conduct experiments. Mini HoK is highly efficient, allowing experiments to be run on personal PCs or laptops while still presenting sufficient challenges for existing MARL algorithms. We have tested our environment on common MARL algorithms and demonstrated that these algorithms have yet to surpass the performance of rule based policies, indicating that current MARL methods are not able to solve this environment. This facilitates the dissemination and advancement of MARL methods within the research community. In addition, we hope that more researchers will leverage the <italic>Honor of Kings</i> map editor to develop innovative and scientifically valuable new maps.","PeriodicalId":55977,"journal":{"name":"IEEE Transactions on Games","volume":"17 3","pages":"787-796"},"PeriodicalIF":2.8,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145073395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yuchen Li;Ziqi Wang;Qingquan Zhang;Bo Yuan;Jialin Liu
This paper comprehensively reviews the metrics for measuring the diversity of game scenarios, spotlighting the innovative use of procedural content generation and other fields as cornerstones for enriching player experiences through diverse game scenarios. By traversing a wide array of disciplines, from affective modeling and multiagent systems to psychological studies, our research underscores the importance of diverse game scenarios in gameplay and education. Through a taxonomy of diversity metrics and evaluation methods, we aim to bridge the current gaps in literature and practice, offering insights into effective strategies for measuring and integrating diversity in game scenarios. Our analysis highlights the necessity for a unified taxonomy to aid developers and researchers in crafting more engaging and varied game worlds. This survey not only charts a path for future research in diverse game scenarios but also serves as a handbook for industry practitioners seeking to leverage diversity as a key component of game design and development.
{"title":"Measuring Diversity of Game Scenarios","authors":"Yuchen Li;Ziqi Wang;Qingquan Zhang;Bo Yuan;Jialin Liu","doi":"10.1109/TG.2025.3543135","DOIUrl":"https://doi.org/10.1109/TG.2025.3543135","url":null,"abstract":"This paper comprehensively reviews the metrics for measuring the diversity of game scenarios, spotlighting the innovative use of procedural content generation and other fields as cornerstones for enriching player experiences through diverse game scenarios. By traversing a wide array of disciplines, from affective modeling and multiagent systems to psychological studies, our research underscores the importance of diverse game scenarios in gameplay and education. Through a taxonomy of diversity metrics and evaluation methods, we aim to bridge the current gaps in literature and practice, offering insights into effective strategies for measuring and integrating diversity in game scenarios. Our analysis highlights the necessity for a unified taxonomy to aid developers and researchers in crafting more engaging and varied game worlds. This survey not only charts a path for future research in diverse game scenarios but also serves as a handbook for industry practitioners seeking to leverage diversity as a key component of game design and development.","PeriodicalId":55977,"journal":{"name":"IEEE Transactions on Games","volume":"17 3","pages":"558-581"},"PeriodicalIF":2.8,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145073221","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Games often incorporate random elements in the form of dice or shuffled card decks. This randomness is a key contributor to the player experience and the variety of game situations encountered. There is a tension between a level of randomness that makes the game interesting and contributes to the player's enjoyment of a game, and a level at which the outcome itself is effectively random and the game becomes dull. The optimal level for a game will depend on the design goals and target audience. We introduce a new technique to quantify the level of randomness in game outcome and use it to compare 15 tabletop games and disentangle the different contributions to the overall randomness from specific parts of some games. We further explore the interaction between game randomness and player skill, and how this innate randomness can affect error analysis in common game experiments.
{"title":"Seeding for Success: Skill and Stochasticity in Tabletop Games","authors":"James Goodman;Diego Perez-Liebana;Simon Lucas","doi":"10.1109/TG.2025.3542263","DOIUrl":"https://doi.org/10.1109/TG.2025.3542263","url":null,"abstract":"Games often incorporate random elements in the form of dice or shuffled card decks. This randomness is a key contributor to the player experience and the variety of game situations encountered. There is a tension between a level of randomness that makes the game interesting and contributes to the player's enjoyment of a game, and a level at which the outcome itself is effectively random and the game becomes dull. The optimal level for a game will depend on the design goals and target audience. We introduce a new technique to quantify the level of randomness in game outcome and use it to compare 15 tabletop games and disentangle the different contributions to the overall randomness from specific parts of some games. We further explore the interaction between game randomness and player skill, and how this innate randomness can affect error analysis in common game experiments.","PeriodicalId":55977,"journal":{"name":"IEEE Transactions on Games","volume":"17 3","pages":"777-786"},"PeriodicalIF":2.8,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145073294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Reinforcement learning has achieved remarkable success across diverse scenarios. However, learning optimal policies within partially observable games remains a formidable challenge. Crucial privileged information in states is often shrouded during gameplay, yet ideally, it should be accessible and exploitable during training. Previous studies have concentrated on formulating policies based wholly on partial observations or oracle states. Nevertheless, these approaches often face hindrances in attaining effective generalization. To surmount this challenge, we propose the actor–cross-critic (ACC) learning framework, integrating both partial observations and oracle states. ACC achieves this by coordinating two critics and invoking a maximization operation mechanism to switch between them dynamically. This approach encourages the selection of the higher values when computing advantages within the actor–critic framework, thereby accelerating learning and mitigating bias under partial observability. Some theoretical analyses show that ACC exhibits better learning ability toward optimal policies than actor–critic learning using the oracle states. We highlight its superior performance through comprehensive evaluations in decision-making tasks, such as QuestBall, Minigrid, and Atari, and the challenging card game DouDizhu.
{"title":"Leveraging Privileged Information for Partially Observable Reinforcement Learning","authors":"Jinqiu Li;Enmin Zhao;Tong Wei;Junliang Xing;Shiming Xiang","doi":"10.1109/TG.2025.3542158","DOIUrl":"https://doi.org/10.1109/TG.2025.3542158","url":null,"abstract":"Reinforcement learning has achieved remarkable success across diverse scenarios. However, learning optimal policies within partially observable games remains a formidable challenge. Crucial privileged information in states is often shrouded during gameplay, yet ideally, it should be accessible and exploitable during training. Previous studies have concentrated on formulating policies based wholly on partial observations or oracle states. Nevertheless, these approaches often face hindrances in attaining effective generalization. To surmount this challenge, we propose the actor–cross-critic (ACC) learning framework, integrating both partial observations and oracle states. ACC achieves this by coordinating two critics and invoking a maximization operation mechanism to switch between them dynamically. This approach encourages the selection of the higher values when computing advantages within the actor–critic framework, thereby accelerating learning and mitigating bias under partial observability. Some theoretical analyses show that ACC exhibits better learning ability toward optimal policies than actor–critic learning using the oracle states. We highlight its superior performance through comprehensive evaluations in decision-making tasks, such as <italic>QuestBall</i>, <italic>Minigrid</i>, and <italic>Atari</i>, and the challenging card game <italic>DouDizhu</i>.","PeriodicalId":55977,"journal":{"name":"IEEE Transactions on Games","volume":"17 3","pages":"765-776"},"PeriodicalIF":2.8,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145073436","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kai Yan;Xianyi Chen;Qi Cui;Haoqin Yuan;Zhenshan Tan
AI-based automatic aiming cheats (a.k.a., AI aimbots) have proliferated in First-Person Shooter games, which grant malicious users an unfair gameplay advantage. Since AI aimbots operate independently of game data and are developed using object detection algorithms, they are difficult to detect with traditional anti-cheating methods. To actively counter AI aimbots, we propose AdvMap, which introduces invisible adversarial perturbations into game scene elements. In optimizing these adversarial perturbations, we design a mixture-of-misleading loss function that increases the total target confidence score within each misleading bounding box. It mitigates the risk of segment missing even when AdvMap is obscured, thereby enhancing the robustness. Besides, an L1-norm constraint with a small scale is employed during each update of the adversarial perturbations, which preserves the fidelity of the game scene. In addition, to enable effective adaptation to interact with various elements within game environments, we introduce an image-subspace-based multidirectional optimization strategy. It enables the adversarial perturbations to adaptively fit into each element by leveraging the mapping relationship between the game's 3-D scenes and its corresponding 2-D images. Furthermore, we construct a comprehensive benchmark, which includes various FPS games with different graphics styles and perspectives. Extensive experimental results demonstrate the efficacy of our method in countering various AI aimbot tools on different state-of-the-art object detection methods.
{"title":"AdvMap: Crafting Adversarial Maps to Counter AI Aimbot in First-Person Shooter Games","authors":"Kai Yan;Xianyi Chen;Qi Cui;Haoqin Yuan;Zhenshan Tan","doi":"10.1109/TG.2025.3537824","DOIUrl":"https://doi.org/10.1109/TG.2025.3537824","url":null,"abstract":"AI-based automatic aiming cheats (a.k.a., AI aimbots) have proliferated in <italic>First-Person Shooter</i> games, which grant malicious users an unfair gameplay advantage. Since AI aimbots operate independently of game data and are developed using object detection algorithms, they are difficult to detect with traditional anti-cheating methods. To actively counter AI aimbots, we propose <monospace>AdvMap</monospace>, which introduces invisible adversarial perturbations into game scene elements. In optimizing these adversarial perturbations, we design a mixture-of-misleading loss function that increases the total target confidence score within each misleading bounding box. It mitigates the risk of segment missing even when <monospace>AdvMap</monospace> is obscured, thereby enhancing the robustness. Besides, an L1-norm constraint with a small scale is employed during each update of the adversarial perturbations, which preserves the fidelity of the game scene. In addition, to enable effective adaptation to interact with various elements within game environments, we introduce an image-subspace-based multidirectional optimization strategy. It enables the adversarial perturbations to adaptively fit into each element by leveraging the mapping relationship between the game's 3-D scenes and its corresponding 2-D images. Furthermore, we construct a comprehensive benchmark, which includes various FPS games with different graphics styles and perspectives. Extensive experimental results demonstrate the efficacy of our method in countering various AI aimbot tools on different state-of-the-art object detection methods.","PeriodicalId":55977,"journal":{"name":"IEEE Transactions on Games","volume":"17 3","pages":"753-764"},"PeriodicalIF":2.8,"publicationDate":"2025-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145073207","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Covert communication has numerous applications across various domains, including the military, the Internet of Things, blockchain, and beyond. Among these, the covert communication method that exploits the unique cover types inherent in single-player games has garnered substantial attention from researchers. However, existing methods are unsuitable for the current social media such as audio and video and traditional blogs, poor interactivity, and player communication content can easily cause unnatural behavior of game characters. For this reason, a covert communication framework based on live broadcast bullet comment games is proposed. Within the framework, the sender initially applies arithmetic encoding to compress the confidential message. Then, the processed message is transformed into the content and time attributes of the bullet comment, adhering to the game's rules. Finally, these bullet comments are sent to the designated live broadcast game room. The receiver extracts the bullet comments sent by the sending party in real time and converts them into confident messages. As a representative of the framework, ${mathit{Plants vs. Zombies}}$, is utilized as an example. Experimental results have identified the optimal method for sending game bullet comments, balancing detection resistance and transmission speed. The proposed approach offers notable advantages in security interactivity and transmission speed, with 4.1 times faster than existing processes.
{"title":"CovLBCG: A Covert Communication Framework Using Live Broadcast Bullet Comment Game","authors":"Chun Mao;Zhenyu Li;Xiangyang Luo","doi":"10.1109/TG.2025.3535684","DOIUrl":"https://doi.org/10.1109/TG.2025.3535684","url":null,"abstract":"Covert communication has numerous applications across various domains, including the military, the Internet of Things, blockchain, and beyond. Among these, the covert communication method that exploits the unique cover types inherent in single-player games has garnered substantial attention from researchers. However, existing methods are unsuitable for the current social media such as audio and video and traditional blogs, poor interactivity, and player communication content can easily cause unnatural behavior of game characters. For this reason, a covert communication framework based on live broadcast bullet comment games is proposed. Within the framework, the sender initially applies arithmetic encoding to compress the confidential message. Then, the processed message is transformed into the content and time attributes of the bullet comment, adhering to the game's rules. Finally, these bullet comments are sent to the designated live broadcast game room. The receiver extracts the bullet comments sent by the sending party in real time and converts them into confident messages. As a representative of the framework, <inline-formula><tex-math>${mathit{Plants vs. Zombies}}$</tex-math></inline-formula>, is utilized as an example. Experimental results have identified the optimal method for sending game bullet comments, balancing detection resistance and transmission speed. The proposed approach offers notable advantages in security interactivity and transmission speed, with 4.1 times faster than existing processes.","PeriodicalId":55977,"journal":{"name":"IEEE Transactions on Games","volume":"17 3","pages":"729-742"},"PeriodicalIF":2.8,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145073318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mahjong is a four-player stochastic imperfect-information game. In this article, we utilize importance sampling within Monte Carlo tree search (MCTS) to enhance the playing strength of our Mahjong program, MeowCaTS. First, we propose a tree structure called the merging solitary tile model, which facilitates the application of importance sampling. This model also reduces the branching factor of the search tree. Second, we apply importance sampling to MCTS and introduce the calculation of importance weights during the backpropagation stage. Finally, we design a multidepth transposition table to accumulate simulation results of similar positions in MCTS, further enhancing the strength of MeowCaTS. In the experiments, the performance of the proposed methods was analyzed, and the results showed a significant improvement. Notably, MeowCaTS won the first place in Computer Olympiad 2023.
{"title":"Applying Importance Sampling to MCTS for Mahjong","authors":"Shih-Chieh Tang;Jr-Chang Chen;I-Chen Wu","doi":"10.1109/TG.2025.3535740","DOIUrl":"https://doi.org/10.1109/TG.2025.3535740","url":null,"abstract":"<italic>Mahjong</i> is a four-player stochastic imperfect-information game. In this article, we utilize importance sampling within Monte Carlo tree search (MCTS) to enhance the playing strength of our <italic>Mahjong</i> program, <sc>MeowCaTS</small>. First, we propose a tree structure called the merging solitary tile model, which facilitates the application of importance sampling. This model also reduces the branching factor of the search tree. Second, we apply importance sampling to MCTS and introduce the calculation of importance weights during the backpropagation stage. Finally, we design a multidepth transposition table to accumulate simulation results of similar positions in MCTS, further enhancing the strength of <sc>MeowCaTS</small>. In the experiments, the performance of the proposed methods was analyzed, and the results showed a significant improvement. Notably, <sc>MeowCaTS</small> won the first place in Computer Olympiad 2023.","PeriodicalId":55977,"journal":{"name":"IEEE Transactions on Games","volume":"17 3","pages":"743-752"},"PeriodicalIF":2.8,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145073272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Since 2010, ARTigo has been leveraging games with a purpose (GWAPs) to engage citizen scientists in the tagging of artworks. In these games, two players collaboratively annotate images under time constraints. This paper introduces ARTigo as an easily customizable framework for image labeling tailored to elicit specific domain knowledge. It also outlines a two-pronged evaluation strategy to assess the impact of ARTigo’s front-end design on visual aesthetics, usability, and cognitive workload, as well as on users' tagging behavior. Comparisons between ARTigo version $boldsymbol {1}$, developed from 2010 to 2013, and version $boldsymbol {2}$, developed in 2022, indicate significant improvements: the System Usability Scale rating improved from grade B to A-, and the Short Visual Aesthetics of Websites Inventory rating from 4.42 to 5.34 points ($boldsymbol {p < 0.05}$). Moreover, the graphical user interface in version $boldsymbol {2}$ promotes more frequent and complex tagging, thus collecting a similar amount of tags with higher entropy in fewer rounds—which is especially beneficial for GWAP with smaller, active communities.
{"title":"ARTigo: Lessons From Social Image Tagging in an Art-Historical Game With a Purpose","authors":"Stefanie Schneider","doi":"10.1109/TG.2025.3534618","DOIUrl":"https://doi.org/10.1109/TG.2025.3534618","url":null,"abstract":"Since 2010, <italic>ARTigo</i> has been leveraging games with a purpose (GWAPs) to engage citizen scientists in the tagging of artworks. In these games, two players collaboratively annotate images under time constraints. This paper introduces <italic>ARTigo</i> as an easily customizable framework for image labeling tailored to elicit specific domain knowledge. It also outlines a two-pronged evaluation strategy to assess the impact of <italic>ARTigo</i>’s front-end design on visual aesthetics, usability, and cognitive workload, as well as on users' tagging behavior. Comparisons between <italic>ARTigo</i> version <inline-formula><tex-math>$boldsymbol {1}$</tex-math></inline-formula>, developed from 2010 to 2013, and version <inline-formula><tex-math>$boldsymbol {2}$</tex-math></inline-formula>, developed in 2022, indicate significant improvements: the System Usability Scale rating improved from grade <italic>B</i> to <italic>A-</i>, and the Short Visual Aesthetics of Websites Inventory rating from 4.42 to 5.34 points (<inline-formula><tex-math>$boldsymbol {p < 0.05}$</tex-math></inline-formula>). Moreover, the graphical user interface in version <inline-formula><tex-math>$boldsymbol {2}$</tex-math></inline-formula> promotes more frequent and complex tagging, thus collecting a similar amount of tags with higher entropy in fewer rounds—which is especially beneficial for GWAP with smaller, active communities.","PeriodicalId":55977,"journal":{"name":"IEEE Transactions on Games","volume":"17 3","pages":"720-728"},"PeriodicalIF":2.8,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145073242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Antonio Maciá-Lillo;Antonio Jimeno-Morenilla;Higinio Mora;Eduard Duta
Video games have evolved into a key part of modern culture and a major economic force, with the global market projected to reach ${$}$522.50 billion in 2024. As technology advances, video games increasingly demand high computing power, often requiring specialized hardware for optimal performance. Real-time strategy games, in particular, are computationally intensive, with complex artificial intelligence algorithms that simulate numerous units and behaviors in real-time. Specialized gaming PCs are use a dedicated graphics processing unit (GPU) to run video games. Due to the usefulness of GPUs besides gaming, modern processors usually include an integrated GPU, specially in the laptop market. We propose a hybrid architecture that utilizes both the dedicated GPU and the integrated GPU simultaneously, to accelerate AI and physics simulations in video games. The hybrid approach aims to maximize the utilization of all available resources. The AI and physics computations are offloaded from the dedicated GPU to the integrated GPU. Therefore, the dedicated GPU can be used exclusively for rendering, resulting in improved performance. We implemented this architecture in a custom-built game engine using OpenGL for graphics rendering and OpenCL for general-purpose GPU computations. Experimental results highlight the performance characteristics of the hybrid architecture, including the challenges of working with the two devices and multitenant GPU interference.
{"title":"Hybrid Architecture for AI-Based RTS Games","authors":"Antonio Maciá-Lillo;Antonio Jimeno-Morenilla;Higinio Mora;Eduard Duta","doi":"10.1109/TG.2025.3533949","DOIUrl":"https://doi.org/10.1109/TG.2025.3533949","url":null,"abstract":"Video games have evolved into a key part of modern culture and a major economic force, with the global market projected to reach <inline-formula><tex-math>${$}$</tex-math></inline-formula>522.50 billion in 2024. As technology advances, video games increasingly demand high computing power, often requiring specialized hardware for optimal performance. Real-time strategy games, in particular, are computationally intensive, with complex artificial intelligence algorithms that simulate numerous units and behaviors in real-time. Specialized gaming PCs are use a dedicated graphics processing unit (GPU) to run video games. Due to the usefulness of GPUs besides gaming, modern processors usually include an integrated GPU, specially in the laptop market. We propose a hybrid architecture that utilizes both the dedicated GPU and the integrated GPU simultaneously, to accelerate AI and physics simulations in video games. The hybrid approach aims to maximize the utilization of all available resources. The AI and physics computations are offloaded from the dedicated GPU to the integrated GPU. Therefore, the dedicated GPU can be used exclusively for rendering, resulting in improved performance. We implemented this architecture in a custom-built game engine using OpenGL for graphics rendering and OpenCL for general-purpose GPU computations. Experimental results highlight the performance characteristics of the hybrid architecture, including the challenges of working with the two devices and multitenant GPU interference.","PeriodicalId":55977,"journal":{"name":"IEEE Transactions on Games","volume":"17 3","pages":"686-699"},"PeriodicalIF":2.8,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10854898","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145073396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：