# Safety-Critical Reinforcement Learning with Viability-Based Action Shielding for Hypersonic Longitudinal Flight

arXiv: https://arxiv.org/abs/2602.03968 · HTML: https://mlsanity.com/paper/2602.03968/

## 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 9 of its 27 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Placed in

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

## Builds on (most cited first, 9 of 9)

- [Constrained Policy Optimization](https://mlsanity.com/paper/1705.10528/) (2017)
- [Safe Reinforcement Learning via Shielding](https://mlsanity.com/paper/1708.08611/) (2017)
- [A Closer Look at Invalid Action Masking in Policy Gradient Algorithms](https://mlsanity.com/paper/2006.14171/) (2020)
- [Lyapunov-based Safe Policy Optimization for Continuous Control](https://mlsanity.com/paper/1901.10031/) (2019)
- [Reinforcement Learning for UAV Attitude Control](https://mlsanity.com/paper/1804.04154/) (2018)
- [A Survey of Safe Reinforcement Learning and Constrained MDPs: A Technical Survey on Single-Agent and Multi-Agent Safety](https://mlsanity.com/paper/2505.17342/) (2025)
- [Probabilistically safe and efficient model-based reinforcement learning](https://mlsanity.com/paper/2504.00626/) (2025)
- [Adaptive Approach Phase Guidance for a Hypersonic Glider via Reinforcement Meta Learning](https://mlsanity.com/paper/2107.14764/) (2021)
- [Deep Reinforcement Learning for Weapons to Targets Assignment in a Hypersonic strike](https://mlsanity.com/paper/2310.18509/) (2023)

## Abstract (arXiv)

This paper presents a safety-critical reinforcement learning framework for nonlinear dynamical systems with continuous state and input spaces operating under explicit physical constraints. Hard safety constraints are enforced independently of the reward through action shielding and reachability-based admissible action sets, ensuring that unsafe behaviors are never intentionally selected during learning or execution. To capture nominal operation and recovery behavior within a single control architecture, the state space is partitioned into safe and unsafe regions based on membership in a safety box, and a mode-dependent reward is used to promote accurate tracking inside the safe region and recovery toward it when operating outside. To enable online tabular learning on continuous dynamics, a finite-state abstraction is constructed via state aggregation, and action selection and value updates are consistently restricted to admissible actions. The framework is demonstrated on a longitudinal point-mass hypersonic vehicle model with aerodynamic and propulsion couplings, using angle of attack and throttle as control inputs.