Manipulation skill learning on multi-step complex task based on explicit and implicit curriculum learning

被引：9

作者：

Liu, Naijun ^{[1
,2
]}

Lu, Tao ^{[1
]}

Cai, Yinghao ^{[1
]}

Wang, Rui ^{[1
]}

Wang, Shuo ^{[1
,2
,3
]}

机构：

[1] Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China

[2] Univ Chinese Acad Sci, Beijing 100049, Peoples R China

[3] CAS Ctr Excellence Brain Sci & Intelligence Techn, Shanghai 200031, Peoples R China

来源：

SCIENCE CHINA-INFORMATION SCIENCES | 2022年 / 65卷 / 01期

基金：

中国国家自然科学基金;

关键词：

Complex task - Learning mechanism - Learning methods - Learning techniques - Multi-step - Skill learning;

D O I：

10.1007/s11432-019-2648-7

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Conclusion We proposed a TATD-HER curriculum learning method to learn manipulation skills on multi-step complex tasks. The method addresses the complicated task with both explicit and implicit curriculum learning mechanisms. The experimental results demonstrate the effectiveness of our proposed TATD-HER method and show that the combination of explicit and implicit curriculum learning techniques is crucial for learning complex manipulation skills. Future work involves applying our method to more complex tasks.

引用

页数：3

共 50 条

[1] Manipulation skill learning on multi-step complex task based on explicit and implicit curriculum learning
Naijun LIU
Tao LU
Yinghao CAI
Rui WANG
Shuo WANG
[J]. Science China(Information Sciences), 2022, 65 (01) : 259 - 261
[2] Manipulation skill learning on multi-step complex task based on explicit and implicit curriculum learning
Naijun Liu
Tao Lu
Yinghao Cai
Rui Wang
Shuo Wang
[J]. Science China Information Sciences, 2022, 65
[3] Multi-step Forecasting via Multi-task Learning
Jawed, Shayan
Rashed, Ahmed
Schmidt-Thieme, Lars
[J]. 2019 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2019, : 790 - 799
[4] An exploration of implicit and explicit learning and skill level in complex dynamic systems
NiDhiomasaigh, L
McCarthy, J
[J]. IRISH JOURNAL OF PSYCHOLOGY, 1995, 16 (04): : 322 - 333
[5] Dynamics Learning with Cascaded Variational Inference for Multi-Step Manipulation
Fang, Kuan
Zhu, Yuke
Garg, Animesh
Savarese, Silvio
Li Fei-Fei
[J]. CONFERENCE ON ROBOT LEARNING, VOL 100, 2019, 100
[6] Learning Implicit and Explicit Multi-task Interactions for Information Extraction
Sun, Kai
Zhang, Richong
Mensah, Samuel
Mao, Yongyi
Liu, Xudong
[J]. ACM TRANSACTIONS ON INFORMATION SYSTEMS, 2023, 41 (02)
[7] IMPLICIT LEARNING IN A COMPLEX TRACKING SKILL
MAGILL, RA
GREEN, KJ
[J]. BULLETIN OF THE PSYCHONOMIC SOCIETY, 1989, 27 (06) : 488 - 488
[8] The role of actions in implicit and explicit motor skill learning
Witt, J
Willingham, D
[J]. JOURNAL OF COGNITIVE NEUROSCIENCE, 2005, : 100 - 100
[9] Skill Learning and Task Outcome Prediction for Manipulation
Pastor, Peter
Kalakrishnan, Mrinal
Chitta, Sachin
Theodorou, Evangelos
Schaal, Stefan
[J]. 2011 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2011,
[10] Multi-step Q learning algorithm for task scheduling in collaborative design
Chen, Shenglei
Wu, Huizhong
Xiao, Liang
Zhu, Yaoqin
[J]. Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 2007, 19 (03): : 398 - 402

← 1 2 3 4 5 →