Quantile Geometry Regularization for Distributional Reinforcement Learning

• URL: http://arxiv.org/abs/2605.08182v1
• Date: Tue, 05 May 2026 09:38:34 GMT
• Title: Quantile Geometry Regularization for Distributional Reinforcement Learning
• Abstract summary: We propose Robust Quantile-based Implicit Quantile Networks (RQIQN)<n>We first reinterpret a snapshot of IQN loss as a collection of local empirical quantile estimation problems over sampled current fractions.<n>We then robustify each local slot with a Wasserstein distributionally robust quantile estimation formulation, yielding a closed-form, fraction-dependent correction to the Bellman target.
• Score: 20.41658533815372
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quantile-based distributional reinforcement learning methods learn return distributions through sampled quantile regression, but their bootstrapped target quantiles may induce distorted or degenerate distribution estimates. We propose Robust Quantile-based Implicit Quantile Networks (RQIQN), a lightweight Wasserstein distributionally robust enhancement boosted from a quantile estimation perspective. We first reinterpret a snapshot of IQN loss as a collection of local empirical quantile estimation problems over sampled current fractions. We then robustify each local slot with a Wasserstein distributionally robust quantile estimation formulation, yielding a closed-form, fraction-dependent correction to the Bellman target. This correction directly addresses distributional degeneration: its median antisymmetry preserves the risk-neutral quantile average, while its monotonicity enlarges upper-lower quantile gaps and counteracts collapsed distributional spread. RQIQN thus regularizes quantile geometry without changing the underlying value objective or requiring additional sample set reconstruction. Finally, we empirically show that the proposed RQIQN outperforms other existing quantile-based distributional reinforcement learning algorithms in risk-sensitive navigation and Atari games.

Related papers

• Non-Crossing Deep Quantile Regression for Distributional Survival Prediction [27.498297952127533]
  Quantile-based modeling instead describes the full conditional distribution on the original time scale.<n>We propose a Censored Non-crossing Quantile (CNQ) framework for right-censored data.<n>It jointly estimates several conditional survival quantiles and guarantees valid ordering by construction.
  arXiv  Detail & Related papers  (2026-08-17T17:46:41Z)
• Semiparametric conformal prediction [79.6147286161434]
  We construct a conformal prediction set accounting for the joint correlation structure of the vector-valued non-conformity scores.<n>We flexibly estimate the joint cumulative distribution function (CDF) of the scores.<n>Our method yields desired coverage and competitive efficiency on a range of real-world regression problems.
  arXiv  Detail & Related papers  (2024-11-04T14:29:02Z)
• 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)
• Distributional Reinforcement Learning with Dual Expectile-Quantile Regression [51.87411935256015]
  quantile regression approach to distributional RL provides flexible and effective way of learning arbitrary return distributions.<n>We show that distributional estimation guarantees vanish, and we empirically observe that the estimated distribution rapidly collapses to its mean.<n>Motivated by the efficiency of $L$-based learning, we propose to jointly learn expectiles and quantiles of the return distribution in a way that allows efficient learning.
  arXiv  Detail & Related papers  (2023-05-26T12:30:05Z)
• QuantProb: Generalizing Probabilities along with Predictions for a Pre-trained Classifier [1.8488661947561271]
  We argue that the reason for unreliability of deep networks is - The way neural networks are currently trained, the probabilities do not generalize across small distortions. We propose an innovative approach to decouple the construction of quantile representations from the loss function allowing us to compute quantile based probabilities without disturbing the original network.
  arXiv  Detail & Related papers  (2023-04-25T12:39:45Z)
• Random Forest Weighted Local Fréchet Regression with Random Objects [18.128663071848923]
  We propose a novel random forest weighted local Fr'echet regression paradigm.<n>Our first method uses these weights as the local average to solve the conditional Fr'echet mean.<n>Second method performs local linear Fr'echet regression, both significantly improving existing Fr'echet regression methods.
  arXiv  Detail & Related papers  (2022-02-10T09:10:59Z)
• Deep Non-Crossing Quantiles through the Partial Derivative [0.6299766708197883]
  Quantile Regression provides a way to approximate a single conditional quantile. Minimisation of the QR-loss function does not guarantee non-crossing quantiles. We propose a generic deep learning algorithm for predicting an arbitrary number of quantiles.
  arXiv  Detail & Related papers  (2022-01-30T15:35:21Z)
• Learning Quantile Functions without Quantile Crossing for Distribution-free Time Series Forecasting [12.269597033369557]
  We propose the Incremental (Spline) Quantile Functions I(S)QF, a flexible and efficient distribution-free quantile estimation framework. We also provide a generalization error analysis of our proposed approaches under the sequence-to-sequence setting.
  arXiv  Detail & Related papers  (2021-11-12T06:54:48Z)
• Unrolling Particles: Unsupervised Learning of Sampling Distributions [102.72972137287728]
  Particle filtering is used to compute good nonlinear estimates of complex systems. We show in simulations that the resulting particle filter yields good estimates in a wide range of scenarios.
  arXiv  Detail & Related papers  (2021-10-06T16:58:34Z)
• A Cram\'er Distance perspective on Non-crossing Quantile Regression in Distributional Reinforcement Learning [2.28438857884398]
  Quantile-based methods like QR-DQN project arbitrary distributions onto a parametric subset of staircase distributions. We show that monotonicity constraints on the quantiles have been shown to improve the performance of QR-DQN for uncertainty-based exploration strategies. We propose a novel non-crossing neural architecture that allows a good training performance using a novel algorithm to compute the Cram'er distance.
  arXiv  Detail & Related papers  (2021-10-01T17:00:25Z)
• Sampling-free Variational Inference for Neural Networks with Multiplicative Activation Noise [51.080620762639434]
  We propose a more efficient parameterization of the posterior approximation for sampling-free variational inference. Our approach yields competitive results for standard regression problems and scales well to large-scale image classification tasks.
  arXiv  Detail & Related papers  (2021-03-15T16:16:18Z)
• Regularization Strategies for Quantile Regression [8.232258589877942]
  We show that minimizing an expected pinball loss over a continuous distribution of quantiles is a good regularizer even when only predicting a specific quantile. We show that lattice models enable regularizing the predicted distribution to a location-scale family.
  arXiv  Detail & Related papers  (2021-02-09T21:10:35Z)
• Nonparametric Score Estimators [49.42469547970041]
  Estimating the score from a set of samples generated by an unknown distribution is a fundamental task in inference and learning of probabilistic models. We provide a unifying view of these estimators under the framework of regularized nonparametric regression. We propose score estimators based on iterative regularization that enjoy computational benefits from curl-free kernels and fast convergence.
  arXiv  Detail & Related papers  (2020-05-20T15:01:03Z)

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.