2019 IEEE Conference on Games (CoG)最新文献_第2页

Action Spaces in Deep Reinforcement Learning to Mimic Human Input Devices 模仿人类输入设备的深度强化学习中的动作空间

2019 IEEE Conference on Games (CoG) Pub Date : 2019-08-01 DOI: 10.1109/CIG.2019.8848080

Marco Pleines, Frank Zimmer, Vincent-Pierre Berges

{"title":"Action Spaces in Deep Reinforcement Learning to Mimic Human Input Devices","authors":"Marco Pleines, Frank Zimmer, Vincent-Pierre Berges","doi":"10.1109/CIG.2019.8848080","DOIUrl":"https://doi.org/10.1109/CIG.2019.8848080","url":null,"abstract":"Enabling agents to generally play video games requires to implement a common action space that mimics human input devices like a gamepad. Such action spaces have to support concurrent discrete and continuous actions. To solve this problem, this work investigates three approaches to examine the application of concurrent discrete and continuous actions in Deep Reinforcement Learning (DRL). One approach implements a threshold to discretize a continuous action, while another one divides a continuous action into multiple discrete actions. The third approach creates a multiagent to combine both action kinds. These approaches are benchmarked by two novel environments. In the first environment (Shooting Birds) the goal of the agent is to accurately shoot birds by controlling a cross-hair. The second environment is a simplification of the game Beastly Rivals On-slaught, where the agent is in charge of its controlled character’s survival. Throughout multiple experiments, the bucket approach is recommended, because it is trained faster than the multiagent and is more stable than the threshold approach. Due to the contributions of this paper, consecutive work can start training agents using visual observations.","PeriodicalId":177208,"journal":{"name":"2019 IEEE Conference on Games (CoG)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124489847","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: 4

Predicting the monetization percentage with survival analysis in free-to-play games 通过生存分析预测免费游戏的盈利比例

2019 IEEE Conference on Games (CoG) Pub Date : 2019-08-01 DOI: 10.1109/CIG.2019.8848045

Riikka Numminen, Markus Viljanen, T. Pahikkala

引用次数: 2

Evolution of Kiting Behavior in a Two Player Combat Problem 双人战斗问题中放风筝行为的演变

2019 IEEE Conference on Games (CoG) Pub Date : 2019-08-01 DOI: 10.1109/CIG.2019.8848124

Pavlos Androulakakis, Zachariah E. Fuchs

引用次数: 1

An Analysis of Peer Presence Social Group Dynamics to Enhance Player Engagement in Multiplayer Games 在多人游戏中同伴存在的社会群体动态分析，以提高玩家粘性

2019 IEEE Conference on Games (CoG) Pub Date : 2019-08-01 DOI: 10.1109/CIG.2019.8848078

Mitchell Miller, Noah Paige, Guraik Clair, C. Eckhardt

{"title":"An Analysis of Peer Presence Social Group Dynamics to Enhance Player Engagement in Multiplayer Games","authors":"Mitchell Miller, Noah Paige, Guraik Clair, C. Eckhardt","doi":"10.1109/CIG.2019.8848078","DOIUrl":"https://doi.org/10.1109/CIG.2019.8848078","url":null,"abstract":"In this paper, we seek to identify game design paradigms that enhance the player experience for multiplayer games in regards to engagement and immersion through social group dynamic emphasized level design based on peer presence. In order to identify these paradigms, we developed a 2D platform game consisting of several scenarios designed to invoke different sub-categories of peer presence social group dynamics such as group cohesion, peer pressure, leader-observer social identity role distribution and black sheep effects. We argue that risk and reward core game mechanics can be carried out or reinforced by the social group dynamics phenomena. A group of participants was monitored through gameplay, and administered surveys prior to, as well as following the game experience.Our study successfully found game design patterns which highlight specific behaviors within group dynamics, especially group cohesion and time-sensitive decision making with regards to peer pressure, which, compared to the single-player control group, increase players engagement and immersion during multiplayer gameplay. Our investigations into these player behavior patterns aim to help game designers enhance player experience in multiplayer games.","PeriodicalId":177208,"journal":{"name":"2019 IEEE Conference on Games (CoG)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132976180","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: 4

Hyperstate Space Graphs for Automated Game Analysis 用于自动博弈分析的超状态空间图

2019 IEEE Conference on Games (CoG) Pub Date : 2019-08-01 DOI: 10.1109/CIG.2019.8848026

Michael Cook, Azalea Raad

引用次数: 13

Characteristics Study of Dance-charts on Rhythm-based Video Games 基于节奏的电子游戏中舞蹈图表的特征研究

2019 IEEE Conference on Games (CoG) Pub Date : 2019-08-01 DOI: 10.1109/CIG.2019.8848126

Yudai Tsujino, Ryosuke Yamanishi, Y. Yamashita

引用次数: 1

Realtime Adaptive Virtual Reality for Pain Reduction 实时自适应虚拟现实减轻疼痛

2019 IEEE Conference on Games (CoG) Pub Date : 2019-08-01 DOI: 10.1109/CIG.2019.8848119

A. Dingli, Luca Bondin

引用次数: 2

Autoencoder and Evolutionary Algorithm for Level Generation in Lode Runner Lode Runner关卡生成的自编码器和进化算法

2019 IEEE Conference on Games (CoG) Pub Date : 2019-08-01 DOI: 10.1109/CIG.2019.8848076

Sarjak Thakkar, Changxing Cao, Lifan Wang, Tae Jong Choi, J. Togelius

引用次数: 29

RDF* Graph Database as Interlingua for the TextWorld Challenge RDF*图形数据库作为TextWorld挑战的中间语言

2019 IEEE Conference on Games (CoG) Pub Date : 2019-08-01 DOI: 10.1109/CIG.2019.8848012

Guntis Barzdins, D. Gosko, Paulis F. Barzdins, Uldis Lavrinovics, Gints Bernans, E. Celms

引用次数: 3

Searching the Latent Space of a Generative Adversarial Network to Generate DOOM Levels 搜索生成对抗网络的潜在空间以生成DOOM关卡

2019 IEEE Conference on Games (CoG) Pub Date : 2019-08-01 DOI: 10.1109/CIG.2019.8848011

Edoardo Giacomello, P. Lanzi, D. Loiacono

引用次数: 19