Imitation Learning from Video by Leveraging Proprioception

被引:0
|
作者
Torabi, Faraz [1 ]
Warnell, Garrett [2 ]
Stone, Peter [1 ]
机构
[1] Univ Texas Austin, Austin, TX 78712 USA
[2] Army Res Lab, Austin, TX USA
基金
美国国家科学基金会;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Classically, imitation learning algorithms have been developed for idealized situations, e.g., the demonstrations are often required to be collected in the exact same environment and usually include the demonstrator's actions. Recently, however, the research community has begun to address some of these shortcomings by offering algorithmic solutions that enable imitation learning from observation (IfO), e.g., learning to perform a task from visual demonstrations that may be in a different environment and do not include actions. Motivated by the fact that agents often also have access to their own internal states (i.e., proprioception), we propose and study an IfO algorithm that leverages this information in the policy learning process. The proposed architecture learns policies over proprioceptive state representations and compares the resulting trajectories visually to the demonstration data. We experimentally test the proposed technique on several MuJoCo domains and show that it outperforms other imitation from observation algorithms by a large margin.
引用
收藏
页码:3585 / 3591
页数:7
相关论文
共 50 条
  • [31] Leveraging from group classification for video concept detection
    Niaz, Usman
    Merialdo, Bernard
    2013 11TH INTERNATIONAL WORKSHOP ON CONTENT-BASED MULTIMEDIA INDEXING (CBMI 2013), 2013, : 172 - 177
  • [32] Imitation Learning from Humanoids in a Heterogeneous Setting
    Allen, Jeff
    Anderson, John
    Baltes, Jacky
    TRENDS IN INTELLIGENT ROBOTICS, 2010, 103 : 106 - 113
  • [33] Robust Imitation Learning from Noisy Demonstrations
    Tangkaratt, Voot
    Charoenphakdee, Nontawat
    Sugiyama, Masashi
    24TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS (AISTATS), 2021, 130 : 298 - +
  • [34] Learning by imitation
    Basçi, E
    JOURNAL OF ECONOMIC DYNAMICS & CONTROL, 1999, 23 (9-10): : 1569 - 1585
  • [35] Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning
    Li, Ziming
    Kiseleva, Julia
    de Rijke, Maarten
    THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 6722 - 6729
  • [36] Learning from a tutor: embodied speech acquisition and imitation learning
    Vaz, Miguel
    Brand, Holger
    Joublin, Frank
    Goerick, Christian
    2009 IEEE 8TH INTERNATIONAL CONFERENCE ON DEVELOPMENT AND LEARNING, 2009, : 242 - +
  • [37] Recent Advances in Imitation Learning from Observation
    Torabi, Faraz
    Warnell, Garrett
    Stone, Peter
    PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2019, : 6325 - 6331
  • [38] Situated robotics: from learning to teaching by imitation
    Cristina Urdiales
    Ulises Cortés
    Cognitive Processing, 2005, 6 (3) : 196 - 201
  • [39] Adversarial Imitation Learning from Incomplete Demonstrations
    Sun, Mingfei
    Xiaojuan
    PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2019, : 3513 - 3519
  • [40] Leveraging Demonstrator-Perceived Precision for Safe Interactive Imitation Learning of Clearance-Limited Tasks
    Oh, Hanbit
    Matsubara, Takamitsu
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2024, 9 (04) : 3387 - 3394