A Predictive Model for Imitation Learning in Partially Observable Environments

被引：0
|
作者：
Boularias, Abdeslam [1 ]
机构：
[1] Univ Laval, Dept Comp Sci, Ste Foy, PQ G1K 7P4, Canada
来源：
SEVENTH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS, PROCEEDINGS | 2008年
关键词：
D O I：
10.1109/ICMLA.2008.142
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Learning by imitation has shown to be a powerful paradigm for automated learning in autonomous robots. This paper presents a general framework of learning by imitation for stochastic and partially observable systems. The model is a Predictive Policy Representation (PPR) whose goal is to represent the teacher's policies without any reference to states. The model is fully described in terms of actions and observations only. We show how this model can efficiently learn the personal behavior and preferences of an assistive robot user.
引用
收藏
页码：83 / 90
页数：8
相关论文
共 50 条
  • [1] Context Discovery for Model Learning in Partially Observable Environments
    Hemion, Nikolas J.
    [J]. 2016 JOINT IEEE INTERNATIONAL CONFERENCE ON DEVELOPMENT AND LEARNING AND EPIGENETIC ROBOTICS (ICDL-EPIROB), 2016, : 294 - 299
  • [2] Model Predictive Control in Partially Observable Multi-Modal Discrete Environments
    Rosolia, Ugo
    Guastella, Dario C.
    Muscato, Giovanni
    Borrelli, Francesco
    [J]. IEEE CONTROL SYSTEMS LETTERS, 2023, 7 : 2161 - 2166
  • [3] Learning to Make Predictions In Partially Observable Environments Without a Generative Model
    Talvitie, Erik
    Singh, Satinder
    [J]. JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, 2011, 42 : 353 - 392
  • [4] Learning to make predictions in partially observable environments without a generative model
    Talvitie, Erik
    Singh, Satinder
    [J]. Journal of Artificial Intelligence Research, 2011, 42 : 353 - 392
  • [5] Inverse reinforcement learning in partially observable environments
    Choi, Jaedeug
    Kim, Kee-Eung
    [J]. Journal of Machine Learning Research, 2011, 12 : 691 - 730
  • [6] Inverse Reinforcement Learning in Partially Observable Environments
    Choi, Jaedeug
    Kim, Kee-Eung
    [J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2011, 12 : 691 - 730
  • [7] Inverse Reinforcement Learning in Partially Observable Environments
    Choi, Jaedeug
    Kim, Kee-Eung
    [J]. 21ST INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI-09), PROCEEDINGS, 2009, : 1028 - 1033
  • [8] State Representation Learning with Robotic Priors for Partially Observable Environments
    Morik, Marco
    Rastogi, Divyam
    Jonschkowski, Rico
    Brock, Oliver
    [J]. 2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2019, : 6693 - 6699
  • [9] Learning finite-state controllers for partially observable environments
    Meuleau, N
    Peshkin, L
    Kim, KE
    Kaelbling, LP
    [J]. UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 1999, : 427 - 436
  • [10] Learning Navigation Costs from Demonstration in Partially Observable Environments
    Wang, Tianyu
    Dhiman, Vikas
    Atanasov, Nikolay
    [J]. 2020 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2020, : 4434 - 4440
12345