IEEE Transactions on Games最新文献_第2页

Mini Honor of Kings: A Lightweight Environment for Multiagent Reinforcement Learning 迷你王者荣耀：用于多智能体强化学习的轻量级环境

IF 2.8 4区计算机科学

IEEE Transactions on Games Pub Date : 2025-02-27 DOI: 10.1109/TG.2025.3546252

Lin Liu;Jian Zhao;Cheng Hu;Zhengtao Cao;Youpeng Zhao;Zhenbin Ye;Meng Meng;Wenjun Wang;Zhaofeng He;Houqiang Li;Xia Lin;Lanxiao Huang

{"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 and design a lightweight environment, <italic>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 <italic>Honor of Kings 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}

引用次数: 0

Measuring Diversity of Game Scenarios 衡量游戏场景的多样性

IF 2.8 4区计算机科学

IEEE Transactions on Games Pub Date : 2025-02-20 DOI: 10.1109/TG.2025.3543135

Yuchen Li;Ziqi Wang;Qingquan Zhang;Bo Yuan;Jialin Liu

引用次数: 0

Seeding for Success: Skill and Stochasticity in Tabletop Games 为成功播种：桌面游戏中的技能和随机性

IF 2.8 4区计算机科学

IEEE Transactions on Games Pub Date : 2025-02-14 DOI: 10.1109/TG.2025.3542263

James Goodman;Diego Perez-Liebana;Simon Lucas

引用次数: 0

Leveraging Privileged Information for Partially Observable Reinforcement Learning 利用特权信息进行部分可观察强化学习

IF 2.8 4区计算机科学

IEEE Transactions on Games Pub Date : 2025-02-13 DOI: 10.1109/TG.2025.3542158

Jinqiu Li;Enmin Zhao;Tong Wei;Junliang Xing;Shiming Xiang

{"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, <italic>Minigrid, and <italic>Atari, and the challenging card game <italic>DouDizhu.","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}

引用次数: 0

AdvMap: Crafting Adversarial Maps to Counter AI Aimbot in First-Person Shooter Games 在第一人称射击游戏中制作对抗地图以对抗AI Aimbot

IF 2.8 4区计算机科学

IEEE Transactions on Games Pub Date : 2025-01-31 DOI: 10.1109/TG.2025.3537824

Kai Yan;Xianyi Chen;Qi Cui;Haoqin Yuan;Zhenshan Tan

{"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 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}

引用次数: 0

CovLBCG: A Covert Communication Framework Using Live Broadcast Bullet Comment Game CovLBCG：一个使用直播子弹评论游戏的隐蔽通信框架

IF 2.8 4区计算机科学

IEEE Transactions on Games Pub Date : 2025-01-28 DOI: 10.1109/TG.2025.3535684

Chun Mao;Zhenyu Li;Xiangyang Luo

{"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}

引用次数: 0

Applying Importance Sampling to MCTS for Mahjong 重要性抽样在麻将MCTS中的应用

IF 2.8 4区计算机科学

IEEE Transactions on Games Pub Date : 2025-01-28 DOI: 10.1109/TG.2025.3535740

Shih-Chieh Tang;Jr-Chang Chen;I-Chen Wu

引用次数: 0

ARTigo: Lessons From Social Image Tagging in an Art-Historical Game With a Purpose ARTigo：在艺术历史游戏中使用社交图像标签的经验教训

IF 2.8 4区计算机科学

IEEE Transactions on Games Pub Date : 2025-01-27 DOI: 10.1109/TG.2025.3534618

Stefanie Schneider

{"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 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 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’s front-end design on visual aesthetics, usability, and cognitive workload, as well as on users' tagging behavior. Comparisons between <italic>ARTigo 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 to <italic>A-, 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}

引用次数: 0

Hybrid Architecture for AI-Based RTS Games 基于ai的RTS游戏的混合架构

IF 2.8 4区计算机科学

IEEE Transactions on Games Pub Date : 2025-01-27 DOI: 10.1109/TG.2025.3533949

Antonio Maciá-Lillo;Antonio Jimeno-Morenilla;Higinio Mora;Eduard Duta

{"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}

引用次数: 0

Asynchronous Controlled Single-Channel EOG-Based Puzzle Solver Robot 基于异步控制的单通道eog解谜机器人

IF 2.8 4区计算机科学

IEEE Transactions on Games Pub Date : 2025-01-27 DOI: 10.1109/TG.2025.3534425

Prabin K. Panigrahi;Sukant K. Bisoy

{"title":"Asynchronous Controlled Single-Channel EOG-Based Puzzle Solver Robot","authors":"Prabin K. Panigrahi;Sukant K. Bisoy","doi":"10.1109/TG.2025.3534425","DOIUrl":"https://doi.org/10.1109/TG.2025.3534425","url":null,"abstract":"Electrooculography (EOG)-based human–computer interface (HCI) systems have a wide range of applications due to their usability in inferring user's intention through eye movements. Because of limited eye activities, these systems generate limited commands, such as looking up, down, left, and right. The challenge is to utilize EOG signals in strategy-based applications, such as game-playing robots. This article presents a novel asynchronous controlled single-channel EOG-based HCI system that uses eyeblink signals to control a robotic manipulator in solving Guarini's puzzle. A puzzle board and three control buttons are presented in a graphical user interface. The user navigates to a target through a single eyeblink and selects it through a double eyeblink. Two data analysis algorithms, specifically logistic regression model and eyeblink detection module, are used to detect eyeblinks. Two online experiments were conducted with ten healthy subjects. In the screen-based puzzle-solving experiment, we achieved an average accuracy of 95.19% with a short response time (RT) of 0.96 s and an information transfer rate (ITR) of 268.14 bits/min. In the robot-assisted experiment, the proposed system achieved an average accuracy of 92.7%, with an RT of 0.98 s and an ITR of 252.92 bits/min. In both experiments, during the decision (idle) state, the average false positive rate (FPR) is found to be 0.02 events/min. This system generates sufficient commands to control a robotic manipulator in solving the puzzle on the physical puzzle board. In comparison to existing EOG-based gaming systems, the proposed system achieves high accuracy, low RT, lower FPR, and high ITR with fewer electrodes.","PeriodicalId":55977,"journal":{"name":"IEEE Transactions on Games","volume":"17 3","pages":"700-709"},"PeriodicalIF":2.8,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145073400","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}

引用次数: 0