Concepedia

On-policy Learning

On-Policy Learning is a reinforcement learning approach wherein the agent learns the value function or policy based on actions taken by the current policy, distinguishing it from off-policy methods by requiring alignment between the behavior policy and the target policy being evaluated.

95

Publications

11.4K

Citations

338

Authors

111

Institutions

Publications per year

2017–2026

68

Parents

Publications

95

Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor

Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel et al. · arXiv (Cornell University) · 2018 · 3.5K citations · Full text

, , +11

Sigmoid-weighted linear units for neural network function approximation in reinforcement learning

Stefan Elfwing, Eiji Uchibe, Kenji Doya · Neural Networks · 2018 · 1.9K citations · Full text

, , +13

Convergence Results for Single-Step On-Policy Reinforcement-Learning Algorithms

Satinder Singh, Tommi Jaakkola, Michael L. Littman et al. · Machine Learning · 2000 · 625 citations · Full text

, , +12

Fast gradient-descent methods for temporal-difference learning with linear function approximation

Richard S. Sutton, Hamid Reza Maei, Doina Precup et al. · 2009 · 532 citations

, , +14

Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor

Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel et al. · International Conference on Machine Learning · 2018 · 479 citations

, , +11

1–5 of 95

Authors

338

  1. RS
    Richard S. Sutton

    University of Alberta, Canada

    6 publications · 745 citations

    6

    h-index

  2. SL
    Sergey Levine

    University of California, Berkeley, United States

    6 publications · 4.4K citations

    6

    h-index

  3. NH
    Nicolas Heess

    Google (United States), United States

    5 publications · 173 citations

    5

    h-index

  4. PA
    Pieter Abbeel

    University of California, Berkeley, United States

    5 publications · 4K citations

    5

    h-index

  5. AA
    Arun Ahuja

    Icahn School of Medicine at Mount Sinai, United States

    4 publications · 576 citations

    4

    h-index

1–5 of 338

Institutions

111

  1. Google (United States)

    Mountain View, United States

    9 h-index

    47 publications

    5.3K citations

  2. University of Alberta

    Edmonton, Canada

    6 h-index

    20 publications

    3.4K citations

  3. McGill University

    Montreal, Canada

    3 h-index

    3 publications

    1.1K citations

  4. University of California, Berkeley

    Berkeley, United States

    3 h-index

    10 publications

    2K citations

  5. Northeastern University

    Shenyang, China

    3 h-index

    7 publications

    594 citations

  6. Institut national de recherche en sciences et technologies du numérique

    Le Chesnay-Rocquencourt, France

    2 h-index

    3 publications

    134 citations

  7. The University of Texas at Arlington

    Arlington, United States

    2 h-index

    3 publications

    528 citations

  8. University of Massachusetts Amherst

    Amherst Center, United States

    2 h-index

    7 publications

    114 citations

1–8 of 111

Venues

  1. arXiv (Cornell University)

    Repository · 30 publications · 5.6K citations

    22

    h-index

  2. 5

    h-index

  3. Automatica

    2 publications · 261 citations

    2

    h-index

  4. Neurocomputing

    2 publications · 47 citations

    2

    h-index

  5. Uncertainty in Artificial Intelligence

    Conference · 2 publications · 32 citations

    2

    h-index

1–5