# DiffCVaR: Reinforcement Learning for Risk Adaptation via Differentiable CVaR Barrier Functions

arXiv: https://arxiv.org/abs/2605.21257 · HTML: https://mlsanity.com/paper/2605.21257/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Safe and constrained RL, one of 15 directions in Deep reinforcement learning methods.
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 20 May 2026.

## Placed in

- Deep reinforcement learning methods / [Safe and constrained RL](https://mlsanity.com/deeprl/safe-and-constrained-rl/)

## Builds on (most cited first, 26 of 26)

- [OptNet: Differentiable Optimization as a Layer in Neural Networks](https://mlsanity.com/paper/1703.00443/) (2017)
- [Control Barrier Functions: Theory and Applications](https://mlsanity.com/paper/1903.11199/) (2019)
- [Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning](https://mlsanity.com/paper/2108.06266/) (2021)
- [How Should a Robot Assess Risk? Towards an Axiomatic Theory of Risk in Robotics](https://mlsanity.com/paper/1710.11040/) (2017)
- [Safe Reinforcement Learning Using Robust Control Barrier Functions](https://mlsanity.com/paper/2110.05415/) (2021)
- [Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graph](https://mlsanity.com/paper/2203.01821/) (2022)
- [Risk-Conditioned Distributional Soft Actor-Critic for Risk-Sensitive Navigation](https://mlsanity.com/paper/2104.03111/) (2021)
- [Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning](https://mlsanity.com/paper/2405.13863/) (2024)
- [Online Control Barrier Functions for Decentralized Multi-Agent Navigation](https://mlsanity.com/paper/2303.04313/) (2023)
- [DR-MPC: Deep Residual Model Predictive Control for Real-world Social Navigation](https://mlsanity.com/paper/2410.10646/) (2024)
- [Towards Generalizable Safety in Crowd Navigation via Conformal Uncertainty Handling](https://mlsanity.com/paper/2508.05634/) (2025)
- [Integrating Predictive Motion Uncertainties with Distributionally Robust Risk-Aware Control for Safe Robot Navigation in Crowds](https://mlsanity.com/paper/2403.05081/) (2024)
- [Learning to Refine Input Constrained Control Barrier Functions via Uncertainty-Aware Online Parameter Adaptation](https://mlsanity.com/paper/2409.14616/) (2024)
- [Calculating CVaR and bPOE for Common Probability Distributions With Application to Portfolio Optimization and Density Estimation](https://mlsanity.com/paper/1811.11301/) (2018)
- [Risk-Aware Robotics: Tail Risk Measures in Planning, Control, and Verification](https://mlsanity.com/paper/2403.18972/) (2024)
- [Learning to Adapt Control Barrier Functions Under Epistemic and Aleatoric Uncertainty](https://mlsanity.com/paper/2504.03038/) (2025)
- [Probabilistic Control Barrier Functions: Safety in Probability for Discrete-Time Stochastic Systems](https://mlsanity.com/paper/2510.01501/) (2025)
- [Backup-Based Safety Filters: A Comparative Review of Backup CBF, Model Predictive Shielding, and gatekeeper](https://mlsanity.com/paper/2604.02401/) (2026)
- [Wasserstein Distributionally Robust Chance Constrained Trajectory Optimization for Mobile Robots within Uncertain Safe Corridor](https://mlsanity.com/paper/2308.16381/) (2023)
- [Risk-Aware Control of Discrete-Time Stochastic Systems: Integrating Kalman Filter and Worst-case CVaR in Control Barrier Functions](https://mlsanity.com/paper/2312.15638/) (2023)
- [Risk-Aware Non-Myopic Motion Planner for Large-Scale Robotic Swarm Using CVaR Constraints](https://mlsanity.com/paper/2402.16690/) (2024)
- [Safe Navigation in Uncertain Crowded Environments Using Risk Adaptive CVaR Barrier Functions](https://mlsanity.com/paper/2504.06513/) (2025)
- [Multi-Constraint Safe Reinforcement Learning via Closed-form Solution for Log-Sum-Exp Approximation of Control Barrier Functions](https://mlsanity.com/paper/2505.00671/) (2025)
- [Distributionally Robust CVaR-Based Safety Filtering for Motion Planning in Uncertain Environments](https://mlsanity.com/paper/2309.08821/) (2023)
- [Risk-Aware Fixed-Time Stabilization of Stochastic Systems under Measurement Uncertainty](https://mlsanity.com/paper/2403.20258/) (2024)
- [Chance-Constrained Trajectory Planning with Multimodal Environmental Uncertainty](https://mlsanity.com/paper/2503.06779/) (2025)

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

- [DODGER: Safety-Guided Reinforcement Learning for Robot Navigation Among Dynamic Obstacles](https://mlsanity.com/paper/2609.38873/) (2026)

## Abstract (arXiv)

Planning through crowded environments under uncertain obstacle motions remains difficult, as stochastic interactions often induce overly conservative behavior or reduced efficiency. To address this challenge, we propose an end-to-end risk adaptation framework for crowd navigation under obstacle-motion uncertainty modeled by a Gaussian mixture model. The framework combines reinforcement learning~(RL) with a differentiable quadratic-program safety layer based on Conditional Value-at-Risk~(CVaR) barrier functions, jointly learning nominal control input, risk level, and safety margin and enforcing explicit probabilistic safety constraints. This design enables context-aware adaptation, promoting efficient behavior while invoking caution only when necessary. We conduct extensive evaluations in dynamic, uncertain, and crowded environments across varying obstacle densities and robot models, and further assess generalization under three out-of-distribution cases. Comparisons across optimization-based, RL-based, and integrated RL and optimization methods are provided, and the proposed method is shown to deliver the strongest overall performance in safety, efficiency, and generalization under uncertainty.