Concepedia

Value Function Generalization

Value Function Generalization is a theoretical framework within reinforcement learning that characterizes the capacity of a value function to accurately estimate expected returns for previously unencountered states or state-action pairs by leveraging structural assumptions, function approximation, and inductive biases to extend beyond observed data.

89

Publications

7.5K

Citations

235

Authors

95

Institutions

Publications per year

2017–2026

28

Parents

Publications

89

Dueling Network Architectures for Deep Reinforcement Learning

Ziyu Wang, Tom Schaul, Matteo Hessel et al. · arXiv (Cornell University) · 2015 · 1.8K citations · Full text

, , +16

Universal Value Function Approximators

Tom Schaul, Daniel Horgan, Karol Gregor et al. · 2015 · 616 citations

, , +8

Generalization in Reinforcement Learning: Safely Approximating the Value Function

Justin A. Boyan, Andrew Moore · 1994 · 511 citations

, , +11

Explicit Solution of a General Consumption/Investment Problem

Ioannis Karatzas, John P. Lehoczky, Suresh Sethi et al. · Mathematics of Operations Research · 1986 · 388 citations

, , +17

Least-Squares Temporal Difference Learning

Justin A. Boyan · 1999 · 262 citations

, , +15

1–5 of 89

Authors

235

  1. DS
    David Silver

    Google DeepMind (United Kingdom), United Kingdom

    8 publications · 1.3K citations

    8

    h-index

  2. TS
    Tom Schaul

    Google DeepMind (United Kingdom), United Kingdom

    6 publications · 2.9K citations

    6

    h-index

  3. HV
    Hado van Hasselt

    Google DeepMind (United Kingdom), United Kingdom

    4 publications · 2.1K citations

    4

    h-index

  4. RM
    Rémi Munos

    Google (United States), United States

    4 publications · 455 citations

    4

    h-index

  5. SW
    Shimon Whiteson

    University of Oxford, United Kingdom

    4 publications · 162 citations

    4

    h-index

1–5 of 235

Institutions

95

  1. University of Alberta

    Edmonton, Canada

    6 h-index

    11 publications

    462 citations

  2. The University of Texas at Austin

    Austin, United States

    5 h-index

    9 publications

    453 citations

  3. University College London

    London, United Kingdom

    3 h-index

    2 publications

    50 citations

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

    Le Chesnay-Rocquencourt, France

    3 h-index

    3 publications

    252 citations

  5. Stanford University

    Stanford, United States

    3 h-index

    6 publications

    367 citations

  6. Carnegie Mellon University

    Pittsburgh, United States

    3 h-index

    7 publications

    1.9K citations

  7. McGill University

    Montreal, Canada

    2 h-index

    2 publications

    267 citations

  8. Google DeepMind (United Kingdom)

    London, United Kingdom

    2 h-index

    10 publications

    13.4K citations

1–8 of 95

Venues

  1. arXiv (Cornell University)

    Repository · 19 publications · 2.8K citations

    15

    h-index

  2. SIAM Journal on Control and Optimization

    4 publications · 81 citations

    4

    h-index

  3. Mathematics of Operations Research

    4 publications · 466 citations

    4

    h-index

  4. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 2 publications · 39 citations

    3

    h-index

  5. Electronic Journal of Probability

    EJP · 2 publications · 82 citations

    2

    h-index

1–5