Discovering Generalizable Skills via Automated Generation of Diverse Tasks

被引:0
|
作者
Fang, Kuan [1 ]
Zhu, Yuke [2 ,3 ]
Savarese, Silvio [1 ]
Li Fei-Fei [1 ]
机构
[1] Stanford Univ, Stanford, CA 94305 USA
[2] UT Austin, Austin, TX USA
[3] Nvidia, Santa Clara, CA USA
来源
ROBOTICS: SCIENCE AND SYSTEM XVII | 2021年
关键词
REINFORCEMENT; OBJECTS;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The learning efficiency and generalization ability of an intelligent agent can be greatly improved by utilizing a useful set of skills. However, the design of robot skills can often be intractable in real-world applications due to the prohibitive amount of effort and expertise that it requires. In this work, we introduce Skill Learning In Diversified Environments (SLIDE), a method to discover generalizable skills via automated generation of a diverse set of tasks. As opposed to prior work on unsupervised discovery of skills which incentivizes the skills to produce different outcomes in the same environment, our method pairs each skill with a unique task produced by a trainable task generator. To encourage generalizable skills to emerge, our method trains each skill to specialize in the paired task and maximizes the diversity of the generated tasks. A task discriminator defined on the robot behaviors in the generated tasks is jointly trained to estimate the evidence lower bound of the diversity objective. The learned skills can then be composed in a hierarchical reinforcement learning algorithm to solve unseen target tasks. We demonstrate that the proposed method can effectively learn a variety of robot skills in two tabletop manipulation domains. Our results suggest that the learned skills can effectively improve the robot's performance in various unseen target tasks compared to existing reinforcement learning and skill learning methods.
引用
收藏
页数:12
相关论文
共 50 条
  • [31] Improving Automated Evaluation of Open Domain Dialog via Diverse Reference Augmentation
    Gangal, Varun
    Jhamtani, Harsh
    Hovy, Eduard
    Berg-Kirkpatrick, Taylor
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-IJCNLP 2021, 2021, : 4079 - 4090
  • [32] Improving license plate recognition via diverse stylistic plate generation
    Liu, Qi
    Chen, Song-Lu
    Chen, Yu-Xiang
    Yin, Xu-Cheng
    PATTERN RECOGNITION LETTERS, 2024, 183 : 117 - 124
  • [33] Diverse Audio-to-Image Generation via Semantics and Feature Consistency
    Yang, Pei-Tse
    Su, Feng-Guang
    Wang, Yu-Chiang Frank
    2020 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2020, : 1188 - 1192
  • [34] Generation of Diverse Transformed Human Cell Lines Via HiPS Teratoma
    Takahashi, T.
    Kamada, M.
    Kumazaki, T.
    Matsuo, T.
    Mitsui, Y.
    EUROPEAN JOURNAL OF CANCER, 2012, 48 : S95 - S96
  • [35] Exploring Automated Assertion Generation via Large Language Models
    Zhang, Quanjun
    Sun, Weifeng
    Fang, Chunrong
    Yu, Bowen
    Li, Hongyan
    Yan, Meng
    Zhou, Jianyi
    Chen, Zhenyu
    ACM TRANSACTIONS ON SOFTWARE ENGINEERING AND METHODOLOGY, 2025, 34 (03)
  • [36] Automated co-superpixel generation via graph matching
    Yurui Xie
    Lingfeng Xu
    Zhengning Wang
    Signal, Image and Video Processing, 2014, 8 : 753 - 763
  • [37] Automated co-superpixel generation via graph matching
    Xie, Yurui
    Xu, Lingfeng
    Wang, Zhengning
    SIGNAL IMAGE AND VIDEO PROCESSING, 2014, 8 (04) : 753 - 763
  • [38] Towards Automated Memory Model Generation Via Event Tracing
    Perks, O. F. J.
    Beckingsale, D. A.
    Hammond, S. D.
    Miller, I.
    Herdman, J. A.
    Vadgama, A.
    Bhalerao, A. H.
    He, L.
    Jarvis, S. A.
    COMPUTER JOURNAL, 2013, 56 (02): : 156 - 174
  • [39] Handling aperiodic tasks in diverse real-time systems via plug-ins
    Lennvall, T
    Fohler, G
    Lindberg, B
    ISORC 2002: FIFTH IEEE INTERNATIONAL SYMPOSIUM ON OBJECT-ORIENTED REAL-TIME DISTRIBUTED COMPUTING, PROCEEDINGS, 2002, : 137 - 144
  • [40] Invited: Automated Code generation for Information Technology Tasks in YAML through Large Language Models
    Pujar, Saurabh
    Buratti, Luca
    Guo, Xiaojie
    Dupuis, Nicolas
    Lewis, Burn
    Suneja, Sahil
    Sood, Atin
    Nalawade, Ganesh
    Jones, Matt
    Morari, Alessandro
    Puri, Ruchir
    2023 60TH ACM/IEEE DESIGN AUTOMATION CONFERENCE, DAC, 2023,