# ASGARD: Action-Space Guard for UAV Resilience via Reinforcement Learning

arXiv: https://arxiv.org/abs/2609.20982 · HTML: https://mlsanity.com/paper/2609.20982/

## Key facts

- No citing papers in the map yet (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 26 references that are in the map.
- First posted on arXiv 17 Sep 2026.

## 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)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Learning Quadrupedal Locomotion over Challenging Terrain](https://mlsanity.com/paper/2010.11251/) (2020)
- [Robust Adversarial Reinforcement Learning](https://mlsanity.com/paper/1703.02702/) (2017)
- [Learning by Cheating](https://mlsanity.com/paper/1912.12294/) (2019)
- [Adversarial Attacks on Neural Network Policies](https://mlsanity.com/paper/1702.02284/) (2017)
- [End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks](https://mlsanity.com/paper/1903.08792/) (2019)
- [Action Robust Reinforcement Learning and Applications in Continuous Control](https://mlsanity.com/paper/1901.09184/) (2019)
- [Control of a Quadrotor with Reinforcement Learning](https://mlsanity.com/paper/1707.05110/) (2017)
- [Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Control](https://mlsanity.com/paper/2103.02142/) (2021)
- [Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learning](https://mlsanity.com/paper/2001.09684/) (2020)
- [safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Robotics](https://mlsanity.com/paper/2109.06325/) (2021)
- [Robustifying Reinforcement Learning Agents via Action Space Adversarial Training](https://mlsanity.com/paper/2007.07176/) (2020)
- [On the Role of the Action Space in Robot Manipulation Learning and Sim-to-Real Transfer](https://mlsanity.com/paper/2312.03673/) (2023)
- [Query-based Targeted Action-Space Adversarial Policies on Deep Reinforcement Learning Agents](https://mlsanity.com/paper/2011.07114/) (2020)
- [Learning Resilient Behaviors for Navigation Under Uncertainty](https://mlsanity.com/paper/1910.09998/) (2019)
- [SpecGuard: Specification Aware Recovery for Robotic Autonomous Vehicles from Physical Attacks](https://mlsanity.com/paper/2408.15200/) (2024)
- [ARMOR: Robust Reinforcement Learning-based Control for UAVs under Physical Attacks](https://mlsanity.com/paper/2506.22423/) (2025)

## Abstract (arXiv)

Reinforcement learning (RL) controllers have been recently adopted for Unmanned Aerial Vehicles (UAV) navigation and control. However, they are susceptible to action-space attacks that overwrite the action commands after the policy generates them and before the actuators execute them. While most existing defenses target attacks on the policy's inputs, those addressing action-space attacks retrain the policy at training time and are not resilient to corrupted actions at runtime. We propose ASGARD, a two-phase teacher-student pipeline for making RL-based UAV control resilient to action-space attacks. In the teacher phase, an encoder combines the UAV's physical state with action-attack-related privileged information to produce an action-attack-aware latent that trains the RL control policy and a monitor that outputs corrected action commands to the actuators. In the student phase, both the encoder and the monitor are trained via supervised learning from their teacher counterparts to run on-board using only the UAV's physical state history. We evaluate ASGARD across attack scenarios targeting different action commands on UAV. We find that ASGARD is resilient to action-space attacks and completes the missions despite the attack. We further find that ASGARD generalizes to unseen attacks and remains resilient against stealthy attacks.