A Survey of Zero-shot Generalisation in Deep Reinforcement Learning

被引：0
|
作者：
Kirk, Robert [1 ]
Zhang, Amy [2 ,3 ]
Grefenstette, Edward [1 ]
Rocktäschel, Tim [1 ]
机构：
[1] University College London, Gower St, London,WC1E 6BT, United Kingdom
[2] University of California, Berkeley, Berkeley,CA, United States
[3] Meta AI Research, United States
来源：
Journal of Artificial Intelligence Research | 2023年 / 76卷
关键词：
213;
D O I：
10.1613/jair.1.14174
中图分类号：
学科分类号：
摘要：
引用
收藏
页码：201 / 264
相关论文
共 50 条
  • [1] A Survey of Zero-shot Generalisation in Deep Reinforcement Learning
    Kirk, Robert
    Zhang, Amy
    Grefenstette, Edward
    Rocktaeschel, Tim
    [J]. JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, 2023, 76 : 201 - 264
  • [2] Hypernetworks for Zero-Shot Transfer in Reinforcement Learning
    Rezaei-Shoshtari, Sahand
    Morissette, Charlotte
    Hogan, Francois R.
    Dudek, Gregory
    Meger, David
    [J]. THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 8, 2023, : 9579 - 9587
  • [3] Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning
    Oh, Junhyuk
    Singh, Satinder
    Lee, Honglak
    Kohli, Pushmeet
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 70, 2017, 70
  • [4] DARLA: Improving Zero-Shot Transfer in Reinforcement Learning
    Higgins, Irina
    Pal, Arka
    Rusu, Andrei
    Matthey, Loic
    Burgess, Christopher
    Pritzel, Alexander
    Botyinick, Matthew
    Blundell, Charles
    Lerchner, Alexander
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 70, 2017, 70
  • [5] DEEP ZERO-SHOT LEARNING FOR SCENE SKETCH
    Xie, Yao
    Xu, Peng
    Ma, Zhanyu
    [J]. 2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2019, : 3661 - 3665
  • [6] Learning a Deep Embedding Model for Zero-Shot Learning
    Zhang, Li
    Xiang, Tao
    Gong, Shaogang
    [J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 3010 - 3019
  • [7] Constrained GPI for Zero-Shot Transfer in Reinforcement Learning
    Kim, Jaekyeom
    Park, Seohong
    Kim, Gunhee
    [J]. Advances in Neural Information Processing Systems, 2022, 35
  • [8] Combining ontology and reinforcement learning for zero-shot classification
    Liu, Bin
    Yao, Li
    Ding, Zheyuan
    Xu, Junyi
    Wu, Junfeng
    [J]. KNOWLEDGE-BASED SYSTEMS, 2018, 144 : 42 - 50
  • [9] Environment Generation for Zero-Shot Compositional Reinforcement Learning
    Gur, Izzeddin
    Jaques, Natasha
    Miao, Yingjie
    Choi, Jongwook
    Tiwari, Manoj
    Lee, Honglak
    Faust, Aleksandra
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [10] Encoding formulas as deep networks: Reinforcement learning for zero-shot execution of LTL formulas
    Kuo, Yen-Ling
    Katz, Boris
    Barbu, Andrei
    [J]. 2020 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2020, : 5604 - 5610
12345