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
  • [21] Future Challenges in the Assessment of Proprioception in Exercise Sciences: Is Imitation an Alternative?
    Munoz-Jimenez, Jesus
    Rojas-Valverde, Daniel
    Leon, Kiko
    FRONTIERS IN HUMAN NEUROSCIENCE, 2021, 15
  • [22] Proprioception in motor learning: lessons from a deafferented subject
    N. Yousif
    J. Cole
    J. Rothwell
    J. Diedrichsen
    Experimental Brain Research, 2015, 233 : 2449 - 2459
  • [23] Proprioception in motor learning: lessons from a deafferented subject
    Yousif, N.
    Cole, J.
    Rothwell, J.
    Diedrichsen, J.
    EXPERIMENTAL BRAIN RESEARCH, 2015, 233 (08) : 2449 - 2459
  • [24] Reinforced Imitation: Sample Efficient Deep Reinforcement Learning for Mapless Navigation by Leveraging Prior Demonstrations
    Pfeiffer, Mark
    Shukla, Samarth
    Turchetta, Matteo
    Cadena, Cesar
    Krause, Andreas
    Siegwart, Roland
    Nieto, Juan
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2018, 3 (04): : 4423 - 4430
  • [25] LEARNING OF IMITATION AND LEARNING THROUGH IMITATION IN WHITE RAT
    HARUKI, Y
    TSUZUKI, T
    ANNUAL OF ANIMAL PSYCHOLOGY, 1967, 17 (02): : 57 - &
  • [26] Quality-Aware Neural Adaptive Video Streaming With Lifelong Imitation Learning
    Huang, Tianchi
    Zhou, Chao
    Yao, Xin
    Zhang, Rui-Xiao
    Wu, Chenglei
    Yu, Bing
    Sun, Lifeng
    IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2020, 38 (10) : 2324 - 2342
  • [27] Comyco: Quality-Aware Adaptive Video Streaming via Imitation Learning
    Huang, Tianchi
    Zhou, Chao
    Zhang, Rui-Xiao
    Wu, Chenglei
    Yao, Xin
    Sun, Lifeng
    PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19), 2019, : 429 - 437
  • [28] Imitation Learning for Adaptive Video Streaming With Future Adversarial Information Bottleneck Principle
    Wang, Shuoyao
    Lin, Jiawei
    Ye, Fangwei
    IEEE TRANSACTIONS ON MOBILE COMPUTING, 2024, 23 (12) : 13670 - 13683
  • [29] Proprioception-based movement goals support imitation and are disrupted in apraxia
    Isaacs, Mitchell W.
    Buxbaum, Laurel J.
    Wong, Aaron L.
    CORTEX, 2022, 147 : 140 - 156
  • [30] Sequential robot imitation learning from observations
    Tanwani, Ajay Kumar
    Yan, Andy
    Lee, Jonathan
    Calinon, Sylvain
    Goldberg, Ken
    INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2021, 40 (10-11): : 1306 - 1325