Risk-sensitive Policy Learning

Risk-Sensitive Policy Learning is a methodological framework within policy learning that explicitly incorporates risk measures—such as variance, conditional value-at-risk, or entropic risk—into the policy optimization process to prioritize robustness and caution under uncertainty, distinguishing it from risk-neutral approaches by its sensitivity to the distributional characteristics of outcomes.

34

Publications

2K

Citations

81

Authors

50

Institutions

Publications per year

2017–2026

22

Authors

81

  1. AT
    Aviv Tamar

    Technion – Israel Institute of Technology, Israel

    3 publications · 207 citations

    3

    h-index

  2. SM
    Shie Mannor

    Technion – Israel Institute of Technology, Israel

    3 publications · 207 citations

    3

    h-index

  3. JG
    James G. March

    Stanford University, United States

    2 publications · 329 citations

    2

    h-index

  4. AS
    Amrit Singh Bedi

    Indian Institute of Technology Kanpur, India

    2 publications · 23 citations

    2

    h-index

  5. VS
    Vivek S. Borkar

    Tata Institute of Fundamental Research, India

    2 publications · 136 citations

    2

    h-index

1–5 of 81

Venues

  1. arXiv (Cornell University)

    Repository · 6 publications · 133 citations

    6

    h-index

  2. Psychological Review

    2 publications · 329 citations

    2

    h-index

  3. Digital Chemical Engineering

    1 publications · 28 citations

    1

    h-index

  4. The International Journal of Robotics Research

    IJRR · 1 publications · 37 citations

    1

    h-index

  5. 1

    h-index

1–5