Deep reinforcement learning for conversational robots playing games

H. Cuayáhuitl
{"title":"Deep reinforcement learning for conversational robots playing games","authors":"H. Cuayáhuitl","doi":"10.1109/HUMANOIDS.2017.8246959","DOIUrl":null,"url":null,"abstract":"Deep reinforcement learning for interactive multimodal robots is attractive for endowing machines with trainable skill acquisition. But this form of learning still represents several challenges. The challenge that we focus in this paper is effective policy learning. To address that, in this paper we compare the Deep Q-Networks (DQN) method against a variant that aims for stronger decisions than the original method by avoiding decisions with the lowest negative rewards. We evaluated our baseline and proposed algorithms in agents playing the game of Noughts and Crosses with two grid sizes (3×3 and 5×5). Experimental results show evidence that our proposed method can lead to more effective policies than the baseline DQN method, which can be used for training interactive social robots.","PeriodicalId":143992,"journal":{"name":"2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2017-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/HUMANOIDS.2017.8246959","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 8

Abstract

Deep reinforcement learning for interactive multimodal robots is attractive for endowing machines with trainable skill acquisition. But this form of learning still represents several challenges. The challenge that we focus in this paper is effective policy learning. To address that, in this paper we compare the Deep Q-Networks (DQN) method against a variant that aims for stronger decisions than the original method by avoiding decisions with the lowest negative rewards. We evaluated our baseline and proposed algorithms in agents playing the game of Noughts and Crosses with two grid sizes (3×3 and 5×5). Experimental results show evidence that our proposed method can lead to more effective policies than the baseline DQN method, which can be used for training interactive social robots.
会话机器人玩游戏的深度强化学习
交互式多模态机器人的深度强化学习对于赋予机器可训练的技能习得是有吸引力的。但是这种学习方式仍然存在一些挑战。我们在本文中关注的挑战是有效的政策学习。为了解决这个问题,在本文中,我们将Deep Q-Networks (DQN)方法与一种变体进行了比较,该变体通过避免具有最低负奖励的决策来实现比原始方法更强的决策。我们评估了我们的基线,并提出了两种网格大小(3×3和5×5)的智能体玩零叉游戏的算法。实验结果表明,我们提出的方法可以产生比基线DQN方法更有效的策略,可用于训练交互式社交机器人。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信