# Reachability Verification Based Reliability Assessment for Deep Reinforcement Learning Controlled Robotics and Autonomous Systems

arXiv: https://arxiv.org/abs/2210.14991 · HTML: https://mlsanity.com/paper/2210.14991/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 43 references that are in the map.
- First posted on arXiv 26 Oct 2022.

## Builds on (most cited first, 20 of 20)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [Deep Reinforcement Learning for Autonomous Driving: A Survey](https://mlsanity.com/paper/2002.00444/) (2020)
- [Safe Reinforcement Learning via Shielding](https://mlsanity.com/paper/1708.08611/) (2017)
- [Safe Exploration in Continuous Action Spaces](https://mlsanity.com/paper/1801.08757/) (2018)
- [Robust Deep Reinforcement Learning with Adversarial Attacks](https://mlsanity.com/paper/1712.03632/) (2017)
- [Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learning](https://mlsanity.com/paper/2001.08726/) (2020)
- [Reachability Analysis of Deep Neural Networks with Provable Guarantees](https://mlsanity.com/paper/1805.02242/) (2018)
- [Verisig: verifying safety properties of hybrid systems with neural network controllers](https://mlsanity.com/paper/1811.01828/) (2018)
- [A Statistical Approach to Assessing Neural Network Robustness](https://mlsanity.com/paper/1811.07209/) (2018)
- [POLAR: A Polynomial Arithmetic Framework for Verifying Neural-Network Controlled Systems](https://mlsanity.com/paper/2106.13867/) (2021)
- [Towards Scalable Verification of Deep Reinforcement Learning](https://mlsanity.com/paper/2105.11931/) (2021)
- [Statistically Robust Neural Network Classification](https://mlsanity.com/paper/1912.04884/) (2019)
- [Reliability Assessment and Safety Arguments for Machine Learning Components in System Assurance](https://mlsanity.com/paper/2112.00646/) (2021)
- [Assessing the Safety and Reliability of Autonomous Vehicles from Road Testing](https://mlsanity.com/paper/1908.06540/) (2019)
- [Assessing the Reliability of Deep Learning Classifiers Through Robustness Evaluation and Operational Profiles](https://mlsanity.com/paper/2106.01258/) (2021)
- [A Survey of Deep Reinforcement Learning Algorithms for Motion Planning and Control of Autonomous Vehicles](https://mlsanity.com/paper/2105.14218/) (2021)

## Built on by (most cited first, 3 of 3)

- [Probabilistic Robustness in Deep Learning: A Concise yet Comprehensive Guide](https://mlsanity.com/paper/2502.14833/) (2025)
- [TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning](https://mlsanity.com/paper/2506.09562/) (2025)
- [Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation](https://mlsanity.com/paper/2605.14174/) (2026)

## Abstract (arXiv)

Deep Reinforcement Learning (DRL) has achieved impressive performance in robotics and autonomous systems (RAS). A key challenge to its deployment in real-life operations is the presence of spuriously unsafe DRL policies. Unexplored states may lead the agent to make wrong decisions that could result in hazards, especially in applications where DRL-trained end-to-end controllers govern the behaviour of RAS. This paper proposes a novel quantitative reliability assessment framework for DRL-controlled RAS, leveraging verification evidence generated from formal reliability analysis of neural networks. A two-level verification framework is introduced to check the safety property with respect to inaccurate observations that are due to, e.g., environmental noise and state changes. Reachability verification tools are leveraged locally to generate safety evidence of trajectories. In contrast, at the global level, we quantify the overall reliability as an aggregated metric of local safety evidence, corresponding to a set of distinct tasks and their occurrence probabilities. The effectiveness of the proposed verification framework is demonstrated and validated via experiments on real RAS.