mlsanityData to 14 Oct 2026

Eliciting Risk Aversion with Inverse Reinforcement Learning via Interactive Questioning

arXiv 2308.08427 ↗First posted 16 Aug 2023stat.ML cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

We investigate a framework for robo-advisors to estimate non-expert clients' risk aversion using adaptive binary-choice questionnaires. We model risk aversion using cost functions and spectral risk measures in a static setting. We prove the finite-sample identifiability and, for properly designed questions, obtain a convergence rate of √N up to a logarithmic factor, where N is the number of questions. We introduce the notion of distinguishing power and demonstrate, through simulated experiments, that designing questions by maximizing distinguishing power achieves satisfactory accuracy in learning risk aversion with fewer than 50 questions. We also provide a preliminary investigation of an infinite-horizon setting with an additional discount factor for dynamic risk aversion, establishing qualitative identifiability in this case.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 15 of its 42 references that are in the map. First posted on arXiv 16 Aug 2023.

Builds on

15 of 42 references.

References · 15

  1. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 490
  2. 2018A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progresscited by 298
  3. 2021Identifiability in inverse reinforcement learningcited by 55
  4. 2022Invariance in Policy Optimisation and Partial Identifiability in Reward Learningcited by 46
  5. 2017Repeated Inverse Reinforcement Learningcited by 29
  6. 2016Towards Resolving Unidentifiability in Inverse Reinforcement Learningcited by 18
  7. 2017Risk-sensitive Inverse Reinforcement Learning via Semi- and Non-Parametric Methodscited by 12
  8. 2021Risk-averse autonomous systems: A brief history and recent developments from the perspective of optimal controlcited by 12
  9. 2022Conditionally Elicitable Dynamic Risk Measures for Deep Reinforcement Learningcited by 9
  10. 2021Learning from an Exploring Demonstrator: Optimal Reward Estimation for Banditscited by 8
  11. 2016Inverse Optimization of Convex Risk Functionscited by 7
  12. 2021Interactive Inverse Reinforcement Learning for Cooperative Gamescited by 7
3 more
  1. 2022Environment Design for Inverse Reinforcement Learningcited by 4
  2. 2022Risk-Averse Markov Decision Processes through a Distributional Lenscited by 3
  3. 2019Active Learning for Risk-Sensitive Inverse Reinforcement Learningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Distributional Inverse Reinforcement Learningcited by 0
  2. 2026A Noise-Robust Elicit-to-Optimize Framework for Distortion Riskmetrics via Inverse Reinforcement Learningcited by 0