2022 21st Brazilian Symposium on Computer Games and Digital Entertainment (SBGames)最新文献

Procedural Content Generation using Reinforcement Learning and Entropy Measure as Feedback 使用强化学习和熵测度作为反馈的程序内容生成

2022 21st Brazilian Symposium on Computer Games and Digital Entertainment (SBGames) Pub Date : 2022-10-24 DOI: 10.1109/SBGAMES56371.2022.9961076

Paulo Vinícius Moreira Dutra, Saulo Moraes Villela, R. F. Neto

引用次数: 0

A Model for Dynamic Game Content Using Semantic Web and Prolog 基于语义网和Prolog的动态游戏内容模型

2022 21st Brazilian Symposium on Computer Games and Digital Entertainment (SBGames) Pub Date : 2022-10-24 DOI: 10.1109/SBGAMES56371.2022.9961086

Sarah Mattos Tabosa de Almeida, Gabriel Montoto Dutra, G. Fernandes, Jose Ricardo da Silva Junior

{"title":"A Model for Dynamic Game Content Using Semantic Web and Prolog","authors":"Sarah Mattos Tabosa de Almeida, Gabriel Montoto Dutra, G. Fernandes, Jose Ricardo da Silva Junior","doi":"10.1109/SBGAMES56371.2022.9961086","DOIUrl":"https://doi.org/10.1109/SBGAMES56371.2022.9961086","url":null,"abstract":"A common approach for developing video game content is to define it statically. The content is normally created during the game concept layout in order to enable fine control over decisions and story direction, without much space for emergent narrative. For educational games, the narrative can become outdated due to new scientific developments, and may have a low replay value after its concluded. In this paper, we propose a framework capable of collecting data using the semantic web in order to be used as a basis for creating relationships. To do so, we employ Prolog and define facts and rules based on data collected from the semantic web. The proposed approach follows the server-client architecture, allowing multiple clients to work on different data domains and relationships. To evaluate our approach, we developed Dyna Quiz, a trivia-like game that uses dynamically generated content from the semantic web through custom facts and rules considering four domain topics (country, movie, planet, and sport). In addition, we evaluate its latency over network and showed that it takes less than 8 milliseconds to perform 100 inferences at once using a local network, which is sufficient to provide an uninterrupted experience to the final user.","PeriodicalId":154269,"journal":{"name":"2022 21st Brazilian Symposium on Computer Games and Digital Entertainment (SBGames)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123971934","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Design and Architecture of an Open Multiplayer Exergaming Platform called Move2Play 开放式多人游戏平台Move2Play的设计与架构

2022 21st Brazilian Symposium on Computer Games and Digital Entertainment (SBGames) Pub Date : 2022-10-24 DOI: 10.1109/SBGAMES56371.2022.9961109

Flávio R. S. Coutinho, I. S. Silva, G. A. R. Barbosa, Thiago F. Costa, Luis G. D. Carvalho, Cassiano Andrade, João P. S. Pereira, Reynaldo S. G. Pinto, Jonathan H. Silva

引用次数: 0

Line Art Colorization of Fakemon using Generative Adversarial Neural Networks 使用生成对抗神经网络的假emon的线条艺术着色

2022 21st Brazilian Symposium on Computer Games and Digital Entertainment (SBGames) Pub Date : 2022-10-24 DOI: 10.1109/SBGAMES56371.2022.9961078

É. O. Rodrigues, E. Clua, G. B. Vitor

引用次数: 4

CST-Godot: Bridging the Gap Between Game Engines and Cognitive Agents CST-Godot:弥合游戏引擎和认知代理之间的鸿沟

2022 21st Brazilian Symposium on Computer Games and Digital Entertainment (SBGames) Pub Date : 2022-10-24 DOI: 10.1109/SBGAMES56371.2022.9961082

Gustavo Morais, Ian Loron, L. F. Coletta, Anderson A. da Silva, A. Simões, Ricardo Ribeiro Gudwin, P. Costa, E. Colombini

{"title":"CST-Godot: Bridging the Gap Between Game Engines and Cognitive Agents","authors":"Gustavo Morais, Ian Loron, L. F. Coletta, Anderson A. da Silva, A. Simões, Ricardo Ribeiro Gudwin, P. Costa, E. Colombini","doi":"10.1109/SBGAMES56371.2022.9961082","DOIUrl":"https://doi.org/10.1109/SBGAMES56371.2022.9961082","url":null,"abstract":"Cognitive architectures (CA) exist in the neighborhood of research in general AI. However, despite the high importance placed on classical AI techniques in developing complex videogame systems and the success the CA field has had in producing intelligent behavior of different kinds, it has gone largely unexplored in the context of videogame development. This paper presents a framework for implementing cognitive agents based on CAs in the Godot game engine. We employ the Cognitive Systems Toolkit (CST) for this purpose, providing opportunities for development in the academic sphere, primarily for creating experiments and visualizers that take advantage of Godot's physics and rendering libraries. In the context of videogame development, it can help expand upon classical AI techniques and enable more complex and interesting systems' implementation. As a concept proof, we show how a reinforcement learning-based agent can successfully learn how to behave in a game designed under this cognitive environment.","PeriodicalId":154269,"journal":{"name":"2022 21st Brazilian Symposium on Computer Games and Digital Entertainment (SBGames)","volume":"452 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131610218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Message from Computing Track Chairs 来自计算机轨道椅的信息

2022 21st Brazilian Symposium on Computer Games and Digital Entertainment (SBGames) Pub Date : 2022-10-24 DOI: 10.1109/sbgames56371.2022.9961108

引用次数: 0

DRLeague: a Novel 3D Environment for Training Reinforcement Learning Agents DRLeague:一种用于训练强化学习代理的新型3D环境

2022 21st Brazilian Symposium on Computer Games and Digital Entertainment (SBGames) Pub Date : 2022-10-24 DOI: 10.1109/SBGAMES56371.2022.9961113

Hyuan P. Farrapo, R. F. Filho, J. G. R. Maia, P. Serafim

{"title":"DRLeague: a Novel 3D Environment for Training Reinforcement Learning Agents","authors":"Hyuan P. Farrapo, R. F. Filho, J. G. R. Maia, P. Serafim","doi":"10.1109/SBGAMES56371.2022.9961113","DOIUrl":"https://doi.org/10.1109/SBGAMES56371.2022.9961113","url":null,"abstract":"The development of autonomous agents performing unique interactions that resemble human-like behavior is currently driven by Deep Reinforcement Learning (DRL) techniques combined with complex virtual environments. These constitute an active field of research that is fueled by environments usually inspired or borrowed from video games. Although works in the area commonly do not make use of trending 3D games, these games are interesting testbeds for more complex and compelling behaviors, as they tend to explore more variables than their predecessors. This paper introduces DRLeague, a novel DRL environment, proposed to be open-source, and easily customizable, which supports mechanics for 3D games inspired by the popular “car football” game Rocket League. Besides the typical gameplay, we implemented four challenging minigames based on the mechanics from this title with advanced physics simulation and fine-grained car control: penalty shoot, multiplayer penalty shoot, barrier kick, and aerial shoot, each of these requiring more complex skills than the previous ones. Finally, we provide solid baseline experimental results showing the learning progress of agents using Unity's ML-Agents toolkit, evidencing DRLeague as a suitable testbed in the application of machine learning techniques.","PeriodicalId":154269,"journal":{"name":"2022 21st Brazilian Symposium on Computer Games and Digital Entertainment (SBGames)","volume":"164 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114661273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

L2T: An Algorithm to Support The Generation of 2D Texture from LaTeX Math Equations 支持从LaTeX数学方程生成2D纹理的算法

2022 21st Brazilian Symposium on Computer Games and Digital Entertainment (SBGames) Pub Date : 2022-10-24 DOI: 10.1109/SBGAMES56371.2022.9961118

Adriano Aragão dos Santos, E. T. Camargo, R. Scheffel, R. Merli, Eduardo Pezutti, Phyllipe Lima, Heloisa Silva

{"title":"L2T: An Algorithm to Support The Generation of 2D Texture from LaTeX Math Equations","authors":"Adriano Aragão dos Santos, E. T. Camargo, R. Scheffel, R. Merli, Eduardo Pezutti, Phyllipe Lima, Heloisa Silva","doi":"10.1109/SBGAMES56371.2022.9961118","DOIUrl":"https://doi.org/10.1109/SBGAMES56371.2022.9961118","url":null,"abstract":"Serious or educational games for learning mathematics have in common the representation of mathematical equations during the game. However, the tools available to represent an equation in the Unity platform are paid or proprietary. This work introduces L2T, a free and open-source tool capable of reading a LaTeX mathematical expression and generating an equivalent and suitable texture to be displayed in a game scene. The algorithm is divided into two parts. The first part extracts the tokens from the input and builds the Abstract Syntax Tree (AST), while the latter traverses the AST and renders the final texture. The reference implementation is a Unity Script and can be imported as any regular asset. The L2T is currently being used as part of a project to develop a series of educational and serious mathematical games. It was validated within the game “Math Archipelago”, a treasure hunt genre in which the player has to find hidden treasures while solving math problems. The developed solution is essential for creating diverse games for teaching mathematics.","PeriodicalId":154269,"journal":{"name":"2022 21st Brazilian Symposium on Computer Games and Digital Entertainment (SBGames)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121335328","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Computing Track Reviewers 计算轨道评审器

2022 21st Brazilian Symposium on Computer Games and Digital Entertainment (SBGames) Pub Date : 2022-10-24 DOI: 10.1109/sbgames56371.2022.9961083

引用次数: 0

Emotional Tissue: A Visual Representation of Characters' Emotional States in Games 情感组织:游戏中角色情感状态的视觉表现

2022 21st Brazilian Symposium on Computer Games and Digital Entertainment (SBGames) Pub Date : 2022-10-24 DOI: 10.1109/SBGAMES56371.2022.9961085

Jonas De Araújo Luz Junior, M. A. Rodrigues

{"title":"Emotional Tissue: A Visual Representation of Characters' Emotional States in Games","authors":"Jonas De Araújo Luz Junior, M. A. Rodrigues","doi":"10.1109/SBGAMES56371.2022.9961085","DOIUrl":"https://doi.org/10.1109/SBGAMES56371.2022.9961085","url":null,"abstract":"In empathy games, the representation of the character's emotional states during the narrative is relevant. For this purpose, the designer of empathy games uses different resources, such as the game's graphical style, sound and visual effects, soundtrack mood, and narrative style and pace, among others. Although these can effectively transmit emotion, they will still be subject to the player's interpretive subjectivity. However, there are situations where the designer wants the player to understand the character's emotional state, especially when it is the focus of gameplay and fundamental to the player's decisions. Unlike conventional level bars and their visual variations to represent characters' emotional states, this work presents a new approach for defining a widget to express emotional states, modelled as an organic structure in the form of a shaded cloth deformation. We directly relate its pulse frequency to the intensity of the characters' emotions and its colours to the characters' feelings defined by the game designer. In addition, we conducted a preliminary performance comparative study with the widget configured with four, six and eight emotions and created demonstration scenes to validate its use.","PeriodicalId":154269,"journal":{"name":"2022 21st Brazilian Symposium on Computer Games and Digital Entertainment (SBGames)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134641524","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0