# Perturbation-mitigated USV Navigation with Distributionally Robust Reinforcement Learning

arXiv: https://arxiv.org/abs/2512.00030 · HTML: https://mlsanity.com/paper/2512.00030/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods.
- Builds on 18 of its 34 references that are in the map.
- First posted on arXiv 8 Nov 2025.

## Placed in

- Deep reinforcement learning methods / [RL for robot navigation and UAV control](https://mlsanity.com/deeprl/rl-for-robot-navigation-and-uav-control/)

## Builds on (most cited first, 18 of 18)

- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Implicit Quantile Networks for Distributional Reinforcement Learning](https://mlsanity.com/paper/1806.06923/) (2018)
- [Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity](https://mlsanity.com/paper/2208.05767/) (2022)
- [Distributionally Robust Optimization and Generalization in Kernel Methods](https://mlsanity.com/paper/1905.10943/) (2019)
- [Safe Reinforcement Learning with Model Uncertainty Estimates](https://mlsanity.com/paper/1810.08700/) (2018)
- [The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model](https://mlsanity.com/paper/2305.16589/) (2023)
- [An Online Method for A Class of Distributionally Robust Optimization with Non-Convex Objectives](https://mlsanity.com/paper/2006.10138/) (2020)
- [Robust Quadrupedal Locomotion via Risk-Averse Policy Learning](https://mlsanity.com/paper/2308.09405/) (2023)
- [Distributionally Robust Model-based Reinforcement Learning with Large State Spaces](https://mlsanity.com/paper/2309.02236/) (2023)
- [A Comparative Study of Bug Algorithms for Robot Navigation](https://mlsanity.com/paper/1808.05050/) (2018)
- [Robust Unmanned Surface Vehicle Navigation with Distributional Reinforcement Learning](https://mlsanity.com/paper/2307.16240/) (2023)
- [Sample Complexity of Distributionally Robust Off-Dynamics Reinforcement Learning with Online Interaction](https://mlsanity.com/paper/2511.05396/) (2025)
- [Adaptive Risk-Tendency: Nano Drone Navigation in Cluttered Environments with Distributional Reinforcement Learning](https://mlsanity.com/paper/2203.14749/) (2022)
- [HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents](https://mlsanity.com/paper/2503.08241/) (2025)
- [A Dynamic Safety Shield for Safe and Efficient Reinforcement Learning of Navigation Tasks](https://mlsanity.com/paper/2412.04153/) (2024)
- [Nonlinear Model Predictive Control for Enhanced Navigation of Autonomous Surface Vessels](https://mlsanity.com/paper/2403.19028/) (2024)
- [Distributionally Robust Policy Evaluation and Learning for Continuous Treatment with Observational Data](https://mlsanity.com/paper/2501.10693/) (2025)
- [TERL: Large-Scale Multi-Target Encirclement Using Transformer-Enhanced Reinforcement Learning](https://mlsanity.com/paper/2503.12395/) (2025)

## Built on by (most cited first, 1 of 1)

- [Quantile Geometry Regularization for Distributional Reinforcement Learning](https://mlsanity.com/paper/2605.08182/) (2026)

## Abstract (arXiv)

The robustness of Unmanned Surface Vehicles (USV) is crucial when facing unknown and complex marine environments, especially when heteroscedastic observational noise poses significant challenges to sensor-based navigation tasks. Recently, Distributional Reinforcement Learning (DistRL) has shown promising results in some challenging autonomous navigation tasks without prior environmental information. However, these methods overlook situations where noise patterns vary across different environmental conditions, hindering safe navigation and disrupting the learning of value functions. To address the problem, we propose DRIQN to integrate Distributionally Robust Optimization (DRO) with implicit quantile networks to optimize worst-case performance under natural environmental conditions. Leveraging explicit subgroup modeling in the replay buffer, DRIQN incorporates heterogeneous noise sources and target robustness-critical scenarios. Experimental results based on the risk-sensitive environment demonstrate that DRIQN significantly outperforms state-of-the-art methods, achieving +13.51% success rate, -12.28% collision rate and +35.46% for time saving, +27.99% for energy saving, compared with the runner-up.