Concepedia

Demonstration-based Reinforcement Learning

Demonstration-Based Reinforcement Learning is a reinforcement learning paradigm that belongs to the class of imitation learning methods, distinguished by its use of expert demonstrations to guide policy acquisition through reward shaping or direct policy initialization.

81

Publications

4.1K

Citations

241

Authors

86

Institutions

Publications per year

2017–2026

49

Parents

Publications

81

Deep Q-learning From Demonstrations

Todd Hester, Matej Vecerík, Olivier Pietquin et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 2018 · 809 citations · Full text

, , +15

Deep Q-learning from Demonstrations

Todd Hester, Matej Vecerík, Olivier Pietquin et al. · arXiv (Cornell University) · 2017 · 307 citations · Full text

, , +15

Interactive Policy Learning through Confidence-Based Autonomy

Sonia Chernova, Manuela Veloso · Journal of Artificial Intelligence Research · 2009 · 220 citations · Full text

, , +15

Reinforcement learning from demonstration through shaping

Tim Brys, Anna Harutyunyan, Halit Bener Suay et al. · 2015 · 157 citations

, , +15

Integrating reinforcement learning with human demonstrations of varying ability

Matthew E. Taylor, Halit Bener Suay, Sonia Chernova · 2011 · 128 citations

, , +16

1–5 of 81

Authors

241

  1. SC
    Sonia Chernova

    Georgia Institute of Technology, United States

    5 publications · 559 citations

    5

    h-index

  2. ME
    Matthew E. Taylor

    Washington State University, United States

    5 publications · 369 citations

    5

    h-index

  3. HB
    Halit Bener Suay

    Worcester Polytechnic Institute, United States

    4 publications · 339 citations

    4

    h-index

  4. AS
    Adish Singla

    Max Planck Institute for Software Systems, Germany

    4 publications · 117 citations

    4

    h-index

  5. ML
    Marc Lanctot

    Google DeepMind (United Kingdom), United Kingdom

    3 publications · 1.2K citations

    3

    h-index

1–5 of 241

Institutions

86

  1. Google (United States)

    Mountain View, United States

    4 h-index

    32 publications

    15.7K citations

  2. Worcester Polytechnic Institute

    Worcester, United States

    4 h-index

    10 publications

    732 citations

  3. The University of Texas at Austin

    Austin, United States

    4 h-index

    10 publications

    558 citations

  4. Max Planck Institute for Software Systems

    Saarbrücken, Germany

    4 h-index

    11 publications

    313 citations

  5. Georgia Institute of Technology

    Atlanta, United States

    3 h-index

    10 publications

    307 citations

  6. Washington State University

    Pullman, United States

    3 h-index

    5 publications

    275 citations

  7. Massachusetts Institute of Technology

    Cambridge, United States

    3 h-index

    11 publications

    364 citations

  8. Nanyang Technological University

    Singapore, Singapore

    3 h-index

    10 publications

    418 citations

1–8 of 86

Venues

  1. arXiv (Cornell University)

    Repository · 10 publications · 761 citations

    10

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 6 publications · 953 citations

    6

    h-index

  3. IEEE Robotics and Automation Letters

    2 publications · 59 citations

    2

    h-index

  4. Adaptive Agents and Multi-Agents Systems

    Conference · 2 publications · 85 citations

    2

    h-index

  5. Artificial Intelligence

    2 publications · 65 citations

    2

    h-index

1–5