# How to Train your Quadrotor: A Framework for Consistently Smooth and Responsive Flight Control via Reinforcement Learning

arXiv: https://arxiv.org/abs/2012.06656 · HTML: https://mlsanity.com/paper/2012.06656/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Dec 2020.

## Built on by (most cited first, 7 of 7)

- [L2C2: Locally Lipschitz Continuous Constraint towards Stable and Smooth Reinforcement Learning](https://mlsanity.com/paper/2202.07152/) (2022)
- [Data-Efficient Deep Reinforcement Learning for Attitude Control of Fixed-Wing UAVs: Field Experiments](https://mlsanity.com/paper/2111.04153/) (2021)
- [TACO: General Acrobatic Flight Control via Target-and-Command-Oriented Reinforcement Learning](https://mlsanity.com/paper/2503.01125/) (2025)
- [Sim-Anchored Learning for On-the-Fly Adaptation](https://mlsanity.com/paper/2301.06987/) (2023)
- [Closing the Intent-to-Behavior Gap via Fulfillment Priority Logic](https://mlsanity.com/paper/2503.05818/) (2025)
- [SWIM: Compact Environment Representation for Reinforcement Learning Human Swimming](https://mlsanity.com/paper/2605.31120/) (2026)
- [Redesigning Regularization for Effective Policy Smoothing](https://mlsanity.com/paper/2606.13169/) (2026)

## Abstract (arXiv)

We focus on the problem of reliably training Reinforcement Learning (RL) models (agents) for stable low-level control in embedded systems and test our methods on a high-performance, custom-built quadrotor platform. A common but often under-studied problem in developing RL agents for continuous control is that the control policies developed are not always smooth. This lack of smoothness can be a major problem when learning controllers %intended for deployment on real hardware as it can result in control instability and hardware failure. Issues of noisy control are further accentuated when training RL agents in simulation due to simulators ultimately being imperfect representations of reality - what is known as the reality gap. To combat issues of instability in RL agents, we propose a systematic framework, `REinforcement-based transferable Agents through Learning' (RE+AL), for designing simulated training environments which preserve the quality of trained agents when transferred to real platforms. RE+AL is an evolution of the Neuroflight infrastructure detailed in technical reports prepared by members of our research group. Neuroflight is a state-of-the-art framework for training RL agents for low-level attitude control. RE+AL improves and completes Neuroflight by solving a number of important limitations that hindered the deployment of Neuroflight to real hardware. We benchmark RE+AL on the NF1 racing quadrotor developed as part of Neuroflight. We demonstrate that RE+AL significantly mitigates the previously observed issues of smoothness in RL agents. Additionally, RE+AL is shown to consistently train agents that are flight-capable and with minimal degradation in controller quality upon transfer. RE+AL agents also learn to perform better than a tuned PID controller, with better tracking errors, smoother control and reduced power consumption.