mlsanityData to 7 Oct 2026

Policy Gradient Methods for Distortion Risk Measures

arXiv 2107.04422 ↗First posted 9 Jul 2021cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

We propose policy gradient algorithms which learn risk-sensitive policies in a reinforcement learning (RL) framework. Our proposed algorithms maximize the distortion risk measure (DRM) of the cumulative reward in an episodic Markov decision process in on-policy and off-policy RL settings, respectively. We derive a variant of the policy gradient theorem that caters to the DRM objective, and integrate it with a likelihood ratio-based gradient estimation scheme. We derive non-asymptotic bounds that establish the convergence of our proposed algorithms to an approximate stationary point of the DRM objective.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 8 of its 32 references that are in the map. First posted on arXiv 9 Jul 2021.

Builds on

8 of 32 references.

References · 8

  1. 2013Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programmingcited by 716
  2. 2015Risk-Constrained Reinforcement Learning with Percentile Risk Criteriacited by 320
  3. 2013Risk-sensitive Reinforcement Learningcited by 129
  4. 2019Global Convergence of Policy Gradient Methods to (Almost) Locally Optimal Policiescited by 117
  5. 2018Stochastic Variance-Reduced Policy Gradientcited by 103
  6. 2015Policy Gradient for Coherent Risk Measurescited by 74
  7. 2015Cumulative Prospect Theory Meets Reinforcement Learning: Prediction and Controlcited by 34
  8. 2014Policy Gradients for CVaR-Constrained MDPscited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 0; 2024: 1; 2025: 3; 2026: 1.

6 papers.

  1. 2025Risk-Averse Finetuning of Large Language Modelscited by 7
  2. 2025Risk-sensitive Bandits: Arm Mixture Optimality and Regret-efficient Algorithmscited by 3
  3. 2022A policy gradient approach for optimization of smooth risk measurescited by 2
  4. 2024Risk Sensitivity in Markov Games and Multi-Agent Reinforcement Learning: A Systematic Reviewcited by 0
  5. 2025Policy Newton methods for Distortion Riskmetricscited by 0
  6. 2026Reinforcement learning with an expectile-based objectivecited by 0