{"title":"Call for Papers—IEEE Transactions on Games Special Issue on Gaming Applications for Cultural Heritage","authors":"","doi":"10.1109/TG.2024.3368728","DOIUrl":"https://doi.org/10.1109/TG.2024.3368728","url":null,"abstract":"","PeriodicalId":55977,"journal":{"name":"IEEE Transactions on Games","volume":"16 1","pages":"247-248"},"PeriodicalIF":2.3,"publicationDate":"2024-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10474551","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140161266","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}
{"title":"Call for Auxiliary Papers IEEE Conference on Games 2024","authors":"","doi":"10.1109/TG.2024.3371853","DOIUrl":"https://doi.org/10.1109/TG.2024.3371853","url":null,"abstract":"","PeriodicalId":55977,"journal":{"name":"IEEE Transactions on Games","volume":"16 1","pages":"249-249"},"PeriodicalIF":2.3,"publicationDate":"2024-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10474554","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140161176","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}
{"title":"IEEE Transactions on Games Publication Information","authors":"","doi":"10.1109/TG.2024.3369433","DOIUrl":"https://doi.org/10.1109/TG.2024.3369433","url":null,"abstract":"","PeriodicalId":55977,"journal":{"name":"IEEE Transactions on Games","volume":"16 1","pages":"C2-C2"},"PeriodicalIF":2.3,"publicationDate":"2024-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10474502","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140161178","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}
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 article proposes the Nested WFC algorithm framework to reduce time complexity. To avoid conflict and backtracking problems, we offer a complete and subcomplete 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.
{"title":"Nested Wave Function Collapse Enables Large-Scale Content Generation","authors":"Yuhe Nie;Shaoming Zheng;Zhan Zhuang;Julian Togelius","doi":"10.1109/TG.2024.3377637","DOIUrl":"10.1109/TG.2024.3377637","url":null,"abstract":"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 article proposes the Nested WFC algorithm framework to reduce time complexity. To avoid conflict and backtracking problems, we offer a complete and subcomplete tileset preparation strategy, which requires only a small number of tiles to generate infinite, aperiodic, and deterministic content. We use \u0000<italic>Mario</i>\u0000 and \u0000<italic>Carcassonne</i>\u0000 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.","PeriodicalId":55977,"journal":{"name":"IEEE Transactions on Games","volume":"16 4","pages":"892-902"},"PeriodicalIF":1.7,"publicationDate":"2024-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140168596","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}
Traditional methods of video game bug detection, such as manual testing, have been effective, but they can also be time-consuming and costly. While automated bug detection techniques hold great promise for improving testing, they still face several challenges that need to be addressed to be effective in practice. In this work, we introduce a new framework to detect perceptual bugs using a long short-term memory network, which detects bugs in games as anomalies. The detected buggy frames are then clustered to determine the category of the occurred bug. The framework was evaluated on two first person shooter games. We further enhanced the framework by implementing a reinforcement learning agent to autonomously gather datasets, effectively addressing the need for human players to collect data and manually browse through games. The enhancement was performed on a role-playing game. The outcomes obtained validate the effectiveness of the framework.
{"title":"AstroBug: Automatic Game Bug Detection Using Deep Learning","authors":"Elham Azizi;Loutfouz Zaman","doi":"10.1109/TG.2024.3402626","DOIUrl":"10.1109/TG.2024.3402626","url":null,"abstract":"Traditional methods of video game bug detection, such as manual testing, have been effective, but they can also be time-consuming and costly. While automated bug detection techniques hold great promise for improving testing, they still face several challenges that need to be addressed to be effective in practice. In this work, we introduce a new framework to detect perceptual bugs using a long short-term memory network, which detects bugs in games as anomalies. The detected buggy frames are then clustered to determine the category of the occurred bug. The framework was evaluated on two first person shooter games. We further enhanced the framework by implementing a reinforcement learning agent to autonomously gather datasets, effectively addressing the need for human players to collect data and manually browse through games. The enhancement was performed on a role-playing game. The outcomes obtained validate the effectiveness of the framework.","PeriodicalId":55977,"journal":{"name":"IEEE Transactions on Games","volume":"16 4","pages":"793-806"},"PeriodicalIF":1.7,"publicationDate":"2024-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141059866","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}
In reinforcement learning, the agents need to sufficiently explore the environment and efficiently exploit the existing experiences before finding the solution to the tasks, particularly in cooperative multiagent scenarios where the state and action spaces grow exponentially with the number of agents. Hence, enhancing the exploration ability of agents and improving the utilization efficiency of experiences are two critical issues in cooperative multiagent reinforcement learning. We propose a novel method called generative adversarial imitation learning policy gradients (GAILPG). The contributions of GAILPG are as follows: first, we integrate generative adversarial self-imitation learning into the multiagent actor–critic framework to improve the utilization efficiency of experiences, thus further assisting the policy training; second, we design a new curiosity module to enhance the exploration ability of the agents. Experimental results on the StarCraft II micromanagement benchmark demonstrate that GAILPG surpasses state-of-the-art policy-based methods and is even on par with the value-based methods and the ablation experiments validate the reasonability of the discriminator module and the curiosity module encapsulated in our method.
{"title":"GAILPG: Multiagent Policy Gradient With Generative Adversarial Imitation Learning","authors":"Wei Li;Shiyi Huang;Ziming Qiu;Aiguo Song","doi":"10.1109/TG.2024.3375515","DOIUrl":"10.1109/TG.2024.3375515","url":null,"abstract":"In reinforcement learning, the agents need to sufficiently explore the environment and efficiently exploit the existing experiences before finding the solution to the tasks, particularly in cooperative multiagent scenarios where the state and action spaces grow exponentially with the number of agents. Hence, enhancing the exploration ability of agents and improving the utilization efficiency of experiences are two critical issues in cooperative multiagent reinforcement learning. We propose a novel method called generative adversarial imitation learning policy gradients (GAILPG). The contributions of GAILPG are as follows: first, we integrate generative adversarial self-imitation learning into the multiagent actor–critic framework to improve the utilization efficiency of experiences, thus further assisting the policy training; second, we design a new curiosity module to enhance the exploration ability of the agents. Experimental results on the <italic>StarCraft II</i> micromanagement benchmark demonstrate that GAILPG surpasses state-of-the-art policy-based methods and is even on par with the value-based methods and the ablation experiments validate the reasonability of the discriminator module and the curiosity module encapsulated in our method.","PeriodicalId":55977,"journal":{"name":"IEEE Transactions on Games","volume":"17 1","pages":"62-75"},"PeriodicalIF":1.7,"publicationDate":"2024-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140146697","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}
Adrián Mateo-Orcajada;Lucía Abenza-Cano;Juan Pablo Rey-López;Raquel Vaquero-Cristóbal
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 the 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 pregame anxiety and self-confidence. The participants were players in a professional LOL esports team during a SuperLiga Orange spring split. The profile of mood states and competitive state anxiety inventory-2 questionnaires were used. Performance was assessed using in-game variables, such as game result, favorable and unfavorable plays, and kills/deaths/assists ratio. The results showed that no changes were found in the performance of the players according to the pregame iceberg profile. Changes were found in the pre- and postgame 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.
{"title":"The Iceberg Profile Does Not Influence the Performance of Elite League of Legends Players, but Changes With the Events of the Game","authors":"Adrián Mateo-Orcajada;Lucía Abenza-Cano;Juan Pablo Rey-López;Raquel Vaquero-Cristóbal","doi":"10.1109/TG.2024.3377604","DOIUrl":"10.1109/TG.2024.3377604","url":null,"abstract":"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 <italic>League of Legends</i> (LOL). For these reasons, the objectives of the present research were to analyze whether the 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 pregame anxiety and self-confidence. The participants were players in a professional LOL esports team during a SuperLiga Orange spring split. The profile of mood states and competitive state anxiety inventory-2 questionnaires were used. Performance was assessed using in-game variables, such as game result, favorable and unfavorable plays, and kills/deaths/assists ratio. The results showed that no changes were found in the performance of the players according to the pregame iceberg profile. Changes were found in the pre- and postgame 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.","PeriodicalId":55977,"journal":{"name":"IEEE Transactions on Games","volume":"17 1","pages":"76-87"},"PeriodicalIF":1.7,"publicationDate":"2024-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140146973","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}
Febri Abdullah;Pittawat Taveekitworachai;Mury F. Dewantoro;Ruck Thawonmas;Julian Togelius;Jochen Renz
This article summarizes the first ChatGPT4PCG competition held at the 2023 IEEE Conference on Games. The goal of the competition is to explore emergent abilities of publicly available large language models (LLMs) in performing complex tasks related to procedural content generation, specifically physics-based level generation for Angry Birds -like games. Participants are tasked with submitting their prompts for ChatGPT to generate Angry Birds -like game structures that resemble English uppercase characters. A structure is a collection of stacked game objects comprising a part of an entire Angry Birds -like level. A prompt is an input for LLMs, including ChatGPT. Two evaluation metrics, i.e., stability and similarity, are used to evaluate the submitted prompts. Stability measures the sturdiness of a structure to withstand in-game gravity, while similarity measures a structure's resemblance to the target character. With such evaluation, participants are challenged to produce not only character-like but also stable structures by utilizing prompt engineering techniques. Finally, the competition's results are discussed to provide valuable insights for future studies and competitions.
{"title":"The First ChatGPT4PCG Competition","authors":"Febri Abdullah;Pittawat Taveekitworachai;Mury F. Dewantoro;Ruck Thawonmas;Julian Togelius;Jochen Renz","doi":"10.1109/TG.2024.3376429","DOIUrl":"10.1109/TG.2024.3376429","url":null,"abstract":"This article summarizes the first ChatGPT4PCG competition held at the 2023 IEEE Conference on Games. The goal of the competition is to explore emergent abilities of publicly available large language models (LLMs) in performing complex tasks related to procedural content generation, specifically physics-based level generation for \u0000<italic>Angry Birds</i>\u0000-like games. Participants are tasked with submitting their prompts for ChatGPT to generate \u0000<italic>Angry Birds</i>\u0000-like game structures that resemble English uppercase characters. A structure is a collection of stacked game objects comprising a part of an entire \u0000<italic>Angry Birds</i>\u0000-like level. A prompt is an input for LLMs, including ChatGPT. Two evaluation metrics, i.e., stability and similarity, are used to evaluate the submitted prompts. Stability measures the sturdiness of a structure to withstand in-game gravity, while similarity measures a structure's resemblance to the target character. With such evaluation, participants are challenged to produce not only character-like but also stable structures by utilizing prompt engineering techniques. Finally, the competition's results are discussed to provide valuable insights for future studies and competitions.","PeriodicalId":55977,"journal":{"name":"IEEE Transactions on Games","volume":"16 4","pages":"971-980"},"PeriodicalIF":1.7,"publicationDate":"2024-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140115320","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}
Recently, considerable research has been focused on multiagent reinforcement learning to effectively account for each agent's relations. However, most research has focused on homogeneous multiagent systems with the same type of agents, which has limited application to heterogeneous multiagent systems. The demand for heterogeneous systems has considerably increased not only in games but also in the real world. Therefore, a technique that can properly consider relations in heterogeneous systems is required. In this article, we propose a novel transformer network called HRformer, which is based on heterogeneous graph networks that can reflect the heterogeneity and relations among agents. To this end, we design an effective linear encoding method for the transformer to receive input of the various and unique characteristics of the agents and introduce a novel encoding method to model the relations among them. Experiments are conducted in the StarCraft multiagent challenge environment, the most famous heterogeneous multiagent simulation, to demonstrate the superior performance of the proposed method compared with the other existing methods in various heterogeneous scenarios. The proposed method in our simulation shows a high win rate and fast convergence speed, proving the superiority of the proposed method considering the heterogeneity of the multiagent system.
{"title":"A Hetero-Relation Transformer Network for Multiagent Reinforcement Learning","authors":"Junho Park;Sukmin Yoon;Yong-Duk Kim","doi":"10.1109/TG.2024.3399167","DOIUrl":"10.1109/TG.2024.3399167","url":null,"abstract":"Recently, considerable research has been focused on multiagent reinforcement learning to effectively account for each agent's relations. However, most research has focused on homogeneous multiagent systems with the same type of agents, which has limited application to heterogeneous multiagent systems. The demand for heterogeneous systems has considerably increased not only in games but also in the real world. Therefore, a technique that can properly consider relations in heterogeneous systems is required. In this article, we propose a novel transformer network called <italic>HRformer</i>, which is based on heterogeneous graph networks that can reflect the heterogeneity and relations among agents. To this end, we design an effective linear encoding method for the transformer to receive input of the various and unique characteristics of the agents and introduce a novel encoding method to model the relations among them. Experiments are conducted in the <italic>StarCraft</i> multiagent challenge environment, the most famous heterogeneous multiagent simulation, to demonstrate the superior performance of the proposed method compared with the other existing methods in various heterogeneous scenarios. The proposed method in our simulation shows a high win rate and fast convergence speed, proving the superiority of the proposed method considering the heterogeneity of the multiagent system.","PeriodicalId":55977,"journal":{"name":"IEEE Transactions on Games","volume":"17 1","pages":"138-147"},"PeriodicalIF":1.7,"publicationDate":"2024-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140930216","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}
The balancing process for game levels in competitive two-player contexts involves a lot of manual work and testing, particularly for nonsymmetrical game levels. In this work, we frame game balancing as a procedural content generation task and propose an architecture for automatically balancing of tile-based levels within the procedural content generation via reinforcement learning framework (PCGRL) framework. Our architecture is divided into three parts: first, a level generator, second, a balancing agent, and third, a reward modeling simulation. Through repeated simulations, the balancing agent receives rewards for adjusting the level toward a given balancing objective, such as equal win rates for all players. To this end, we propose new swap-based representations to improve the robustness of playability, thereby enabling agents to balance game levels more effectively and quickly compared to traditional PCGRL. By analyzing the agent's swapping behavior, we can infer which tile types have the most impact on the balance. We validate our approach in the neural massively multiplayer online environment in a competitive two-player scenario. In this article, we present improved results, explore the applicability of the method to various forms of balancing beyond equal balancing, compare the performance to another search-based approach, and discuss the application of existing fairness metrics to game balancing.
{"title":"Simulation-Driven Balancing of Competitive Game Levels With Reinforcement Learning","authors":"Florian Rupp;Manuel Eberhardinger;Kai Eckert","doi":"10.1109/TG.2024.3399536","DOIUrl":"10.1109/TG.2024.3399536","url":null,"abstract":"The balancing process for game levels in competitive two-player contexts involves a lot of manual work and testing, particularly for nonsymmetrical game levels. In this work, we frame game balancing as a procedural content generation task and propose an architecture for automatically balancing of tile-based levels within the procedural content generation via reinforcement learning framework (PCGRL) framework. Our architecture is divided into three parts: first, a level generator, second, a balancing agent, and third, a reward modeling simulation. Through repeated simulations, the balancing agent receives rewards for adjusting the level toward a given balancing objective, such as equal win rates for all players. To this end, we propose new swap-based representations to improve the robustness of playability, thereby enabling agents to balance game levels more effectively and quickly compared to traditional PCGRL. By analyzing the agent's swapping behavior, we can infer which tile types have the most impact on the balance. We validate our approach in the neural massively multiplayer online environment in a competitive two-player scenario. In this article, we present improved results, explore the applicability of the method to various forms of balancing beyond equal balancing, compare the performance to another search-based approach, and discuss the application of existing fairness metrics to game balancing.","PeriodicalId":55977,"journal":{"name":"IEEE Transactions on Games","volume":"16 4","pages":"903-913"},"PeriodicalIF":1.7,"publicationDate":"2024-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140929989","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}
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：