Intelligent problem-solving as integrated hierarchical reinforcement learning

强化学习 计算机科学 钢筋 人工智能 业务 工程类 结构工程
作者
Manfred Eppe,Christian Gumbsch,Matthias Kerzel,Phuong Nguyen,Martin V. Butz,Stefan Wermter
出处
期刊:Nature Machine Intelligence [Springer Nature]
卷期号:4 (1): 11-20 被引量:28
标识
DOI:10.1038/s42256-021-00433-9
摘要

According to cognitive psychology and related disciplines, the development of complex problem-solving behaviour in biological agents depends on hierarchical cognitive mechanisms. Hierarchical reinforcement learning is a promising computational approach that may eventually yield comparable problem-solving behaviour in artificial agents and robots. However, to date the problem-solving abilities of many human and non-human animals are clearly superior to those of artificial systems. Here, we propose steps to integrate biologically inspired hierarchical mechanisms to enable advanced problem-solving skills in artificial agents. Therefore, we first review the literature in cognitive psychology to highlight the importance of compositional abstraction and predictive processing. Then we relate the gained insights with contemporary hierarchical reinforcement learning methods. Interestingly, our results suggest that all identified cognitive mechanisms have been implemented individually in isolated computational architectures, raising the question of why there exists no single unifying architecture that integrates them. As our final contribution, we address this question by providing an integrative perspective on the computational challenges to develop such a unifying architecture. We expect our results to guide the development of more sophisticated cognitively inspired hierarchical machine learning architectures.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
战神幽默发布了新的文献求助10
1秒前
1秒前
阿飘发布了新的文献求助10
1秒前
Wen完成签到,获得积分20
3秒前
3秒前
3秒前
3秒前
ding应助辛勤夜安采纳,获得10
4秒前
嘟嘟许完成签到,获得积分10
5秒前
5秒前
阿狸贱贱发布了新的文献求助10
6秒前
可爱玫瑰完成签到,获得积分10
6秒前
朝三暮四发布了新的文献求助50
7秒前
科研通AI2S应助咕咕咕采纳,获得10
8秒前
高文强完成签到,获得积分10
8秒前
欢喜藏今发布了新的文献求助10
8秒前
Ldq完成签到 ,获得积分10
8秒前
Tom完成签到,获得积分10
9秒前
无花果应助、、采纳,获得10
9秒前
Eve完成签到 ,获得积分10
10秒前
10秒前
酷酷山菡完成签到 ,获得积分10
10秒前
11秒前
11秒前
11秒前
赵zhao发布了新的文献求助10
12秒前
ybyb完成签到,获得积分10
12秒前
12秒前
谢谢给谢谢的求助进行了留言
12秒前
12秒前
xdd完成签到,获得积分10
12秒前
康康完成签到 ,获得积分10
13秒前
悲凉的小蚂蚁完成签到,获得积分20
13秒前
13秒前
14秒前
14秒前
14秒前
14秒前
14秒前
高分求助中
Licensing Deals in Pharmaceuticals 2019-2024 3000
Effect of reactor temperature on FCC yield 2000
Very-high-order BVD Schemes Using β-variable THINC Method 1020
PraxisRatgeber: Mantiden: Faszinierende Lauerjäger 800
Near Infrared Spectra of Origin-defined and Real-world Textiles (NIR-SORT): A spectroscopic and materials characterization dataset for known provenance and post-consumer fabrics 610
Mission to Mao: Us Intelligence and the Chinese Communists in World War II 600
MATLAB在传热学例题中的应用 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3304015
求助须知:如何正确求助?哪些是违规求助? 2938091
关于积分的说明 8486715
捐赠科研通 2612226
什么是DOI,文献DOI怎么找? 1426575
科研通“疑难数据库(出版商)”最低求助积分说明 662719
邀请新用户注册赠送积分活动 647276