# Towards Safe Reinforcement Learning with Reduced Conservativeness: A Case Study on Drone Flight Control

arXiv: https://arxiv.org/abs/2608.26852 · HTML: https://mlsanity.com/paper/2608.26852/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Safe and constrained RL, one of 15 directions in Deep reinforcement learning methods.
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 27 Aug 2026.

## Placed in

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

## Builds on (most cited first, 10 of 10)

- [Safe Model-based Reinforcement Learning with Stability Guarantees](https://mlsanity.com/paper/1705.08551/) (2017)
- [Hamilton-Jacobi Reachability: A Brief Overview and Recent Advances](https://mlsanity.com/paper/1709.07523/) (2017)
- [A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems](https://mlsanity.com/paper/1705.01292/) (2017)
- [Neural Lander: Stable Drone Landing Control using Learned Dynamics](https://mlsanity.com/paper/1811.08027/) (2018)
- [Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking](https://mlsanity.com/paper/2205.06750/) (2022)
- [Safe Reinforcement Learning Using Black-Box Reachability Analysis](https://mlsanity.com/paper/2204.07417/) (2022)
- [Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes](https://mlsanity.com/paper/2210.10691/) (2022)
- [Hybrid zonotopes: a new set representation for reachability analysis of mixed logical dynamical systems](https://mlsanity.com/paper/2106.14831/) (2021)
- [Scalable Zonotopic Under-approximation of Backward Reachable Sets for Uncertain Linear Systems](https://mlsanity.com/paper/2107.01724/) (2021)
- [Efficient Backward Reachability Using the Minkowski Difference of Constrained Zonotopes](https://mlsanity.com/paper/2207.04272/) (2022)

## Abstract (arXiv)

Incorporating formal methods into reinforcement learning (RL) has the potential to result in the best of both worlds, combining the robustness of formal guarantees with the adaptability and learning capabilities of RL, though careful design is needed to balance safety and exploration. In this work, we propose a framework to mitigate this loss of exploration while still allowing for the safety of the system to be ensured. Specifically, we introduce a less restrictive method that can reduce the conservativeness of formal methods by refining a disturbance model using online collected data and it evaluates the safety of a learning-based controller, using computationally efficient zonotopic reachability analysis for the safety analysis to facilitate a real-time implementation. We validate the framework in a real-world drone flight through a canyon, where the drone is subjected to unknown external disturbances and the framework is tasked with learning those disturbances online and adjusting the safety guarantees accordingly. The results show that the framework enables a less restrictive online training of learning-based controllers without compromising the safety of the system.