2022 IEEE Conference on Games (CoG)最新文献_第2页

Ordering Levels in Human Computation Games using Playtraces and Level Structure 在人类计算游戏中使用Playtraces和关卡结构来排序关卡

2022 IEEE Conference on Games (CoG) Pub Date : 2022-08-21 DOI: 10.1109/CoG51982.2022.9893702

Anurag Sarkar, Seth Cooper

引用次数: 0

VMAPD: Generate Diverse Solutions for Multi-Agent Games with Recurrent Trajectory Discriminators 基于循环轨迹判别器的多智能体博弈的多元解

2022 IEEE Conference on Games (CoG) Pub Date : 2022-08-21 DOI: 10.1109/CoG51982.2022.9893722

Shiyu Huang, Chao Yu, Bin Wang, Dong Li, Yu Wang, Tingling Chen, Jun Zhu

{"title":"VMAPD: Generate Diverse Solutions for Multi-Agent Games with Recurrent Trajectory Discriminators","authors":"Shiyu Huang, Chao Yu, Bin Wang, Dong Li, Yu Wang, Tingling Chen, Jun Zhu","doi":"10.1109/CoG51982.2022.9893722","DOIUrl":"https://doi.org/10.1109/CoG51982.2022.9893722","url":null,"abstract":"Recent algorithms designed for multi-agent tasks focus on finding a single optimal solution for all the agents. However, in many tasks (e.g., matrix games and transportation dispatching), there may exist more than one optimal solution, while previous algorithms can only converge to one of them. In many practical applications, it is important to develop reasonable agents with diverse behaviors. In this paper, we propose ”variational multi-agent policy diversification” (VMAPD), an on-policy framework for discovering diverse policies for coordination patterns of multiple agents. By taking advantage of latent variables and exploiting the connection between variational inference and multi-agent reinforcement learning, we derive a tractable evidence lower bound (ELBO) on the trajectories of all agents. Our algorithm uses policy iteration to maximize the derived lower bound and can be simply implemented by adding a pseudo reward during centralized learning. And the trained agents do not need to access the pseudo reward during decentralized execution. We demonstrate the effectiveness of our algorithm on several popular multi-agent testbeds. Experimental results show that VMAPD finds more solutions with similar sample complexity compared with other baselines.","PeriodicalId":394281,"journal":{"name":"2022 IEEE Conference on Games (CoG)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122155424","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: 1

Gulliver’s Game: Multiviewer and Vtuber Extreme Asymmetric Game 格列佛的游戏:多观看者和Vtuber极端不对称游戏

2022 IEEE Conference on Games (CoG) Pub Date : 2022-08-21 DOI: 10.1109/cog51982.2022.9893555

Jiahao Li, Ke Fang, Xing Sun, Zhouyi Li, Xinyang Wen, Wai Kin Victor Chan

引用次数: 1

CaiRL: A High-Performance Reinforcement Learning Environment Toolkit 一个高性能的强化学习环境工具包

2022 IEEE Conference on Games (CoG) Pub Date : 2022-08-21 DOI: 10.1109/CoG51982.2022.9893661

Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo

{"title":"CaiRL: A High-Performance Reinforcement Learning Environment Toolkit","authors":"Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo","doi":"10.1109/CoG51982.2022.9893661","DOIUrl":"https://doi.org/10.1109/CoG51982.2022.9893661","url":null,"abstract":"This paper addresses the dire need for a platform that efficiently provides a framework for running reinforcement learning (RL) experiments. We propose the CaiRL Environment Toolkit as an efficient, compatible, and more sustainable alternative for training learning agents and propose methods to develop more efficient environment simulations. There is an increasing focus on developing sustainable artificial intelligence. However, little effort has been made to improve the efficiency of running environment simulations. The most popular development toolkit for reinforcement learning, OpenAI Gym, is built using Python, a powerful but slow programming language. We propose a toolkit written in C++ with the same flexibility level but works orders of magnitude faster to make up for Python's inefficiency. This would drastically cut climate emissions. CaiRL also presents the first reinforcement learning toolkit with a built-in JVM and Flash support for running legacy flash games for reinforcement learning research. We demonstrate the effectiveness of CaiRL in the classic control benchmark, comparing the execution speed to OpenAI Gym. Furthermore, we illustrate that CaiRL can act as a drop-in replacement for OpenAI Gym to leverage significantly faster training speeds because of the reduced environment computation time.","PeriodicalId":394281,"journal":{"name":"2022 IEEE Conference on Games (CoG)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133116927","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

Crowdsourcing Controller - Utilizing Reliable Agents in a Multiplayer Game 众包控制器-在多人游戏中使用可靠的代理

2022 IEEE Conference on Games (CoG) Pub Date : 2022-08-21 DOI: 10.1109/CoG51982.2022.9893597

Kacper Kenji Lesniak, Maria Maistro

{"title":"Crowdsourcing Controller - Utilizing Reliable Agents in a Multiplayer Game","authors":"Kacper Kenji Lesniak, Maria Maistro","doi":"10.1109/CoG51982.2022.9893597","DOIUrl":"https://doi.org/10.1109/CoG51982.2022.9893597","url":null,"abstract":"This paper presents a new use case for continuous crowdsourcing, where multiple players collectively control a single character in a video game. Similar approaches have already been proposed, but they suffer from certain limitations: (1) they simply consider static time frames to group real-time inputs from multiple players; (2) then they aggregate inputs with simple majority vote, i.e., each player is uniformly weighted. We present a continuous crowdsourcing multiplayer game equipped with our Crowdsourcing Controller. The Crowdsourcing Controller addresses the above-mentioned limitations: (1) our Dynamic Input Frame approach groups incoming players’ input in real-time by dynamically adjusting the frame length; (2) our Continuous Reliability System estimates players’ skills by assigning them a reliability score, which is later used in a weighted majority vote to aggregate the final output command. We evaluated our Crowdsourcing Controller offline with simulated players and online with real players. Offline and online experiments show that both components of our Crowdsourcing Controller lead to higher game scores, i.e., longer playing time. Moreover, the Crowdsourcing Controller is able to correctly estimate and update players’ reliability scores.","PeriodicalId":394281,"journal":{"name":"2022 IEEE Conference on Games (CoG)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126037983","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

Quick generation of crosswords using concatenation 使用连接快速生成填字游戏

2022 IEEE Conference on Games (CoG) Pub Date : 2022-08-21 DOI: 10.1109/CoG51982.2022.9893696

J. Dakowski, Piotr Jaworski, Waldemar Wojna

引用次数: 1

Benni’s Forest – a serious game on the challenges of reforestation 本尼的森林——一个关于重新造林挑战的严肃游戏

2022 IEEE Conference on Games (CoG) Pub Date : 2022-08-21 DOI: 10.1109/CoG51982.2022.9893675

Hidde Bolijn, Martin Li, Andries Reurink, Cas van Rijn, Rafael Bidarra

{"title":"Benni’s Forest – a serious game on the challenges of reforestation","authors":"Hidde Bolijn, Martin Li, Andries Reurink, Cas van Rijn, Rafael Bidarra","doi":"10.1109/CoG51982.2022.9893675","DOIUrl":"https://doi.org/10.1109/CoG51982.2022.9893675","url":null,"abstract":"Many people think of reforestation projects as one-dimensional, simply consisting of planting trees. In reality, a reforestation project takes into account a wide variety of factors, of which the three most important are improving soil quality, reducing fire hazard, and ensuring the prosperity of the community. We posit that a simplistic view on such projects is detrimental for a more committed and serious societal awareness and support of sustainable reforestation. Therefore, it is desirable that more people have a better understanding of the interplay of these factors, as they will likely become more involved in reforestation projects. We present Benni’s Forest, a serious game aimed at increasing awareness of the challenges of reforestation projects. Benni’s Forest is a simulation game, in which the player is responsible for a reforestation project, balancing its various factors over the years, deciding on what to do when and where on the terrain, e.g. fertilizing, planting trees, or digging fire ditches. Meanwhile, adverse events, like wildfires or illegal logging, threaten your progress, creating a tension that gives the player a vivid experience of the complexity of the project. As you progress, several scores indicate the quality of your performance, most notably a biodiversity score, representing the amount and variety of trees in the forest. In this way, players receive clear hints to strategize and face each situation with the appropriate measures to grow a biodiverse forest. We evaluated Benni’s Forest conducting a survey amongst players. The results confirm both an increased understanding of the challenges involved in reforestation efforts, and an increased sense of engagement of players with such projects.","PeriodicalId":394281,"journal":{"name":"2022 IEEE Conference on Games (CoG)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130528916","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

Declarative AI design in Unity using Answer Set Programming 使用答案集编程在Unity中进行声明式AI设计

2022 IEEE Conference on Games (CoG) Pub Date : 2022-08-21 DOI: 10.1109/CoG51982.2022.9893603

Denise Angilica, Giovambattista Ianni, Francesco Pacenza

引用次数: 3

Mitigating Cowardice for Reinforcement Learning Agents in Combat Scenarios 在战斗场景中减轻强化学习代理的怯懦

2022 IEEE Conference on Games (CoG) Pub Date : 2022-08-21 DOI: 10.1109/CoG51982.2022.9893546

Steve Bakos, Heidar Davoudi

引用次数: 0

Neighborly: A Sandbox for Simulation-based Emergent Narrative Neighborly:基于模拟的紧急叙述的沙盒

2022 IEEE Conference on Games (CoG) Pub Date : 2022-08-21 DOI: 10.1109/CoG51982.2022.9893631

Shi Johnson-Bey, M. Nelson, Michael Mateas

引用次数: 2