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
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
  • [1] Active Task Randomization: Learning Robust Skills via Unsupervised Generation of Diverse and Feasible Tasks
    Fang, Kuan
    Migimatsu, Toki
    Mandlekar, Ajay
    Fei-Fei, Li
    Bohg, Jeannette
    2023 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, IROS, 2023, : 1924 - 1931
  • [2] Automated Generation of Statistical Tasks
    Gangur, Mikulas
    DIVAI 2018: 12TH INTERNATIONAL SCIENTIFIC CONFERENCE ON DISTANCE LEARNING IN APPLIED INFORMATICS, 2018, : 47 - 58
  • [3] Generalizable Crowd Counting via Diverse Context Style Learning
    Zhao, Wenda
    Wang, Mingyue
    Liu, Yu
    Lu, Huimin
    Xu, Congan
    Yao, Libo
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 32 (08) : 5399 - 5410
  • [4] DisTop: Discovering a Topological Representation to Learn Diverse and Rewarding Skills
    Aubret, Arthur
    Matignon, Laetitia
    Hassas, Salima
    IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS, 2023, 15 (04) : 1905 - 1915
  • [5] An automated skills assessment framework for laparoscopic training tasks
    Sgouros, Nicholas P.
    Loukas, Constantinos
    Koufi, Vassiliki
    Troupis, Theodore G.
    Georgiou, Evangelos
    INTERNATIONAL JOURNAL OF MEDICAL ROBOTICS AND COMPUTER ASSISTED SURGERY, 2018, 14 (01):
  • [6] Automated Trajectory Generation for Robotic Surgical Tasks
    Yang, Ziqi
    Zhang, Ruiyang
    Chen, Junhong
    Zhou, Xuhui
    Ren, Yunxiao
    Tong, Ziyue
    Lo, Benny
    2024 INTERNATIONAL CONFERENCE ON ADVANCED ROBOTICS AND MECHATRONICS, ICARM 2024, 2024, : 39 - 44
  • [7] Generalizable and Explainable Dialogue Generation via Explicit Action Learning
    Huang, Xinting
    Qi, Jianzhong
    Sun, Yu
    Zhang, Rui
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2020, 2020, : 3981 - 3991
  • [8] Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning
    Netanyahu, Aviv
    Shu, Tianmin
    Tenenbaum, Joshua
    Agrawal, Pulkit
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
  • [9] Rapidly Learning Generalizable and Robot-Agnostic Tool-Use Skills for a Wide Range of Tasks
    Qin, Meiying
    Brawer, Jake
    Scassellati, Brian
    FRONTIERS IN ROBOTICS AND AI, 2021, 8
  • [10] Capturing, classification and concept generation for automated maintenance tasks
    Farnsworth, M.
    Torniyama, T.
    CIRP ANNALS-MANUFACTURING TECHNOLOGY, 2014, 63 (01) : 149 - 152