Risk-Sensitive Reinforcement Learning with Smoothed Quantile Objectives

• URL: http://arxiv.org/abs/2608.22227v1
• Date: Sun, 23 Aug 2026 05:41:32 GMT
• Title: Risk-Sensitive Reinforcement Learning with Smoothed Quantile Objectives
• Abstract summary: We develop a model-based optimistic learning algorithm that maintains confidence sets for the transition kernel and plans using a lower-buffered quantile criterion.<n>We prove that the exact point-quantile evaluation and exact lower-buffered quantile evaluation are PP-hard under Turing-time reductions.
• Score: 2.153824429735596
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement Learning (RL) has achieved tremendous success in recent years. However, the classical foundations of RL do not account for the risk sensitivity of the objective function, which is critical in various fields, including healthcare, finance, etc. A popular approach to incorporate risk sensitivity is to optimize a specific quantile of the cumulative reward distribution. However, exact quantile objectives are non-smooth and can change abruptly under small perturbations of the return distribution, making them difficult to optimize reliably when the transition model must be learned from data. Motivated by this instability, we develop UCB-BQRL, a model-based optimistic learning algorithm that maintains confidence sets for the transition kernel and plans using a lower-buffered quantile criterion. The buffered criterion smooths the exact quantile objective by averaging nearby lower quantiles, thereby improving stability under transition-estimation error. To compute the buffered-quantile policy at each episode, we introduce EVI-BQ, an exact dynamic-programming procedure. We establish a high-probability regret bound for UCB-BQRL, which up to logarithmic factors scales as $\mathcal{O}(\mathrm{e}^{τ/ρ_τ}+H^2\sqrt{SAT})$, where $ρ_τ$ is denoted as the root-level left-plateau threshold, which is a problem-dependent constant. Further, we establish an information-theoretic lower bound of $Ω(H/ρ_τ\sqrt{AT})$ for the regret of any algorithm dealing with a quantile objective function. Finally, we prove that the exact point-quantile evaluation and exact lower-buffered quantile evaluation are PP-hard under polynomial-time Turing reductions, even for a fixed policy in a two-state, one-action finite-horizon MDP.

Related papers

• Scalable Lindblad Noise Learning via Stochastic Tensor-Network Simulation [48.887627688666974]
  Learning dissipation rates in large-scale open quantum systems is a major obstacle for near-term quantum technologies.<n>Here, we propose a scalable noise-learning framework for Lindblad dissipation rates that combines a simulation method, the Jump Method (TJM)<n>We demonstrate the approach on two noise models in the Ising model, in which independent dissipation rates are learned for each site up to $N_mathrmsite=16$.<n>This combination of scalable numerics and rigorous theoretical guarantees positions TJM-based noise learning as a practical foundation for characterizing dissipation in large quantum devices.
  arXiv  Detail & Related papers  (2026-08-25T15:07:11Z)
• Distribution-Aware Robust Bilevel Optimization: Quantile-Guided Huber Updates in Two-Timescale Stochastic Approximation [16.106678611834102]
  Bilevel optimization (BLO) is fundamental to hierarchical decision-making but suffers from critical instability under heavy-tailed noise.<n>Existing techniques typically rely on magnitude checks, which fail to distinguish informative geometric signals from outliers.
  arXiv  Detail & Related papers  (2026-06-21T10:57:37Z)
• Optimistic Reinforcement Learning with Quantile Objectives [6.759916334688207]
  UCB-QRL is an optimistic learning algorithm for the $$-quantile objective in finite-horizon Markov decision processes.<n>We show that UCB-QRL yields a high-probability regret bound $mathcal Oleft((2/)H+1HsqrtSATHlog (2SATH/)right.
  arXiv  Detail & Related papers  (2025-11-12T19:01:00Z)
• Beyond Isotonization: Scalable Non-Crossing Quantile Estimation via Neural Networks for Student Growth Percentiles [0.0]
  Student Growth Percentiles (SGPs), widely adopted across U.S. state assessment systems, employ independent quantile regression followed by post-hoc correction.<n>We demonstrate this approach contains a fundamental methodological inconsistency: between independently-estimated, potentially crossed quantiles requires monotonicity.<n>We propose neural network-based multi-quantile regression (NNQR) with shared hidden layers as a practical alternative.
  arXiv  Detail & Related papers  (2025-10-25T19:39:07Z)
• Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum [78.27945336558987]
  Decentralized server (DFL) eliminates reliance on client-client architecture.<n>Non-smooth regularization is often incorporated into machine learning tasks.<n>We propose a novel novel DNCFL algorithm to solve these problems.
  arXiv  Detail & Related papers  (2025-04-17T08:32:25Z)
• Relaxed Quantile Regression: Prediction Intervals for Asymmetric Noise [51.87307904567702]
  Quantile regression is a leading approach for obtaining such intervals via the empirical estimation of quantiles in the distribution of outputs.<n>We propose Relaxed Quantile Regression (RQR), a direct alternative to quantile regression based interval construction that removes this arbitrary constraint.<n>We demonstrate that this added flexibility results in intervals with an improvement in desirable qualities.
  arXiv  Detail & Related papers  (2024-06-05T13:36:38Z)
• Nearly Optimal Latent State Decoding in Block MDPs [74.51224067640717]
  In episodic Block MDPs, the decision maker has access to rich observations or contexts generated from a small number of latent states. We are first interested in estimating the latent state decoding function based on data generated under a fixed behavior policy. We then study the problem of learning near-optimal policies in the reward-free framework.
  arXiv  Detail & Related papers  (2022-08-17T18:49:53Z)
• Understanding the Under-Coverage Bias in Uncertainty Estimation [58.03725169462616]
  quantile regression tends to emphunder-cover than the desired coverage level in reality. We prove that quantile regression suffers from an inherent under-coverage bias. Our theory reveals that this under-coverage bias stems from a certain high-dimensional parameter estimation error.
  arXiv  Detail & Related papers  (2021-06-10T06:11:55Z)
• Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient [62.24615324523435]
  This paper provides a statistical analysis of high-dimensional batch Reinforcement Learning (RL) using sparse linear function approximation. When there is a large number of candidate features, our result sheds light on the fact that sparsity-aware methods can make batch RL more sample efficient.
  arXiv  Detail & Related papers  (2020-11-08T16:48:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.