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
  • [41] Leveraging ensemble machine learning and multimodal video complexity for better prediction of video difficulty in second language
    Alghamdi, Emad A.
    INTERACTIVE LEARNING ENVIRONMENTS, 2024,
  • [42] Psychological Distance Reduces Literal Imitation: Evidence From an Imitation-Learning Paradigm
    Hansen, Jochim
    Alves, Hans
    Trope, Yaacov
    JOURNAL OF EXPERIMENTAL PSYCHOLOGY-HUMAN PERCEPTION AND PERFORMANCE, 2016, 42 (03) : 320 - 330
  • [43] Proprioception and learning of an interception task
    Fleury, M
    Michaud, D
    Bard, C
    Teasdale, N
    Lamarre, Y
    INTERNATIONAL JOURNAL OF PSYCHOLOGY, 1996, 31 (3-4) : 48468 - 48468
  • [44] Leveraging social media and deep learning to detect rare megafauna in video surveys
    Mannocci, Laura
    Villon, Sebastien
    Chaumont, Marc
    Guellati, Nacim
    Mouquet, Nicolas
    Iovan, Corina
    Vigliola, Laurent
    Mouillot, David
    CONSERVATION BIOLOGY, 2022, 36 (01)
  • [45] Leveraging Virtual Attribute Experience in Video Games to Improve Brand Recall and Learning
    Besharat, Ali
    Kumar, Anand
    Lax, John R.
    Rydzik, Eric J.
    JOURNAL OF ADVERTISING, 2013, 42 (2-3) : 170 - 182
  • [46] Learning by experience from others - Social learning and imitation in animals and robots
    Dautenhahn, K
    Nehaniv, CL
    Alissandrakis, A
    ADAPTIVITY AND LEARNING: AN INTERDISCIPLINARY DEBATE, 2003, : 217 - 241
  • [47] InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations
    Li, Yunzhu
    Song, Jiaming
    Ermon, Stefano
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
  • [48] Generative Adversarial Imitation Learning from Failed Experiences
    Zhu, Jiacheng
    Lin, Jiahao
    Wang, Meng
    Chen, Yingfeng
    Fan, Changjie
    Jiang, Chong
    Zhang, Zongzhang
    THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 13997 - 13998
  • [49] Towards imitation learning from a viewpoint of an internal observer
    Yoshikawa, Y
    Asada, M
    Hosoda, K
    EMBODIED ARTIFICIAL INTELLIGENCE, 2004, 3139 : 278 - 283
  • [50] Provably Efficient Imitation Learning from Observation Alone
    Sun, Wen
    Vemula, Anirudh
    Boots, Byron
    Bagnell, J. Andrew
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, 2019, 97