基于记忆高效深度强化学习的Snake博弈自主智能体

Md. Rafat Rahman Tushar, Shahnewaz Siddique
{"title":"基于记忆高效深度强化学习的Snake博弈自主智能体","authors":"Md. Rafat Rahman Tushar, Shahnewaz Siddique","doi":"10.1109/AICT55583.2022.10013603","DOIUrl":null,"url":null,"abstract":"To perform well, Deep Reinforcement Learning (DRL) methods require significant memory resources and computational time. Also, sometimes these systems need additional environment information to achieve a good reward. However, it is more important for many applications and devices to reduce memory usage and computational times than to achieve the maximum reward. This paper presents a modified DRL method that performs reasonably well with compressed imagery data without requiring additional environment information and also uses less memory and time. We have designed a lightweight Convolutional Neural Network (CNN) with a variant of the Q-network that efficiently takes preprocessed image data as input and uses less memory. Furthermore, we use a simple reward mechanism and small experience replay memory so as to provide only the minimum necessary information. Our modified DRL method enables our autonomous agent to play Snake, a classical control game. The results show our model can achieve similar performance as other DRL methods.","PeriodicalId":441475,"journal":{"name":"2022 IEEE 16th International Conference on Application of Information and Communication Technologies (AICT)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Memory Efficient Deep Reinforcement Learning Approach For Snake Game Autonomous Agents\",\"authors\":\"Md. Rafat Rahman Tushar, Shahnewaz Siddique\",\"doi\":\"10.1109/AICT55583.2022.10013603\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"To perform well, Deep Reinforcement Learning (DRL) methods require significant memory resources and computational time. Also, sometimes these systems need additional environment information to achieve a good reward. However, it is more important for many applications and devices to reduce memory usage and computational times than to achieve the maximum reward. This paper presents a modified DRL method that performs reasonably well with compressed imagery data without requiring additional environment information and also uses less memory and time. We have designed a lightweight Convolutional Neural Network (CNN) with a variant of the Q-network that efficiently takes preprocessed image data as input and uses less memory. Furthermore, we use a simple reward mechanism and small experience replay memory so as to provide only the minimum necessary information. Our modified DRL method enables our autonomous agent to play Snake, a classical control game. The results show our model can achieve similar performance as other DRL methods.\",\"PeriodicalId\":441475,\"journal\":{\"name\":\"2022 IEEE 16th International Conference on Application of Information and Communication Technologies (AICT)\",\"volume\":\"48 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-10-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 IEEE 16th International Conference on Application of Information and Communication Technologies (AICT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/AICT55583.2022.10013603\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE 16th International Conference on Application of Information and Communication Technologies (AICT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AICT55583.2022.10013603","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

深度强化学习(DRL)方法需要大量的内存资源和计算时间。此外,有时候这些系统需要额外的环境信息才能获得良好的奖励。然而,对于许多应用程序和设备来说,减少内存使用和计算时间比实现最大回报更重要。本文提出了一种改进的DRL方法,该方法在不需要额外环境信息的情况下对压缩图像数据进行了较好的处理,并且占用了较少的内存和时间。我们设计了一个轻量级的卷积神经网络(CNN),它是q网络的一个变体,可以有效地将预处理的图像数据作为输入,并且使用更少的内存。此外,我们使用一个简单的奖励机制和小的经验重播记忆,以提供最少的必要信息。我们改进的DRL方法使我们的自主代理能够玩Snake,一个经典的控制游戏。结果表明,该模型可以达到与其他DRL方法相似的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
A Memory Efficient Deep Reinforcement Learning Approach For Snake Game Autonomous Agents
To perform well, Deep Reinforcement Learning (DRL) methods require significant memory resources and computational time. Also, sometimes these systems need additional environment information to achieve a good reward. However, it is more important for many applications and devices to reduce memory usage and computational times than to achieve the maximum reward. This paper presents a modified DRL method that performs reasonably well with compressed imagery data without requiring additional environment information and also uses less memory and time. We have designed a lightweight Convolutional Neural Network (CNN) with a variant of the Q-network that efficiently takes preprocessed image data as input and uses less memory. Furthermore, we use a simple reward mechanism and small experience replay memory so as to provide only the minimum necessary information. Our modified DRL method enables our autonomous agent to play Snake, a classical control game. The results show our model can achieve similar performance as other DRL methods.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Developing Voice Chatbot for Learning Maritime English Automated detection of myocardial infarction using ECG-based artificial intelligence models: a systematic review An Ontological Approach to the Development of Analytical Platform Language Toolkits Anomaly Detection in Cyber-Physical Systems based on BiGRU-VAE Interference Resistant Position Awareness for Collision Avoidance in Dense Drones Swarming
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1