# Multitask Reinforcement Learning for Quadcopter Attitude Stabilization and Tracking using Graph Policy

arXiv: https://arxiv.org/abs/2503.08259 · HTML: https://mlsanity.com/paper/2503.08259/

## 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 24 of its 30 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## 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, 24 of 24)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Deep Reinforcement Learning for Autonomous Driving: A Survey](https://mlsanity.com/paper/2002.00444/) (2020)
- [AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles](https://mlsanity.com/paper/1705.05065/) (2017)
- [RMA: Rapid Motor Adaptation for Legged Robots](https://mlsanity.com/paper/2107.04034/) (2021)
- [Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey](https://mlsanity.com/paper/2009.13303/) (2020)
- [Learning to reinforcement learn](https://mlsanity.com/paper/1611.05763/) (2016)
- [Multi-Task Reinforcement Learning with Context-based Representations](https://mlsanity.com/paper/2102.06177/) (2021)
- [Learning by Playing - Solving Sparse Reward Tasks from Scratch](https://mlsanity.com/paper/1802.10567/) (2018)
- [Multi-Task Reinforcement Learning with Soft Modularization](https://mlsanity.com/paper/2003.13661/) (2020)
- [Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control](https://mlsanity.com/paper/2401.16889/) (2024)
- [GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learning](https://mlsanity.com/paper/1810.05762/) (2018)
- [Flightmare: A Flexible Quadrotor Simulator](https://mlsanity.com/paper/2009.00563/) (2020)
- [Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts](https://mlsanity.com/paper/2311.11385/) (2023)
- [Divide-and-Conquer Reinforcement Learning](https://mlsanity.com/paper/1711.09874/) (2017)
- [PaCo: Parameter-Compositional Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2210.11653/) (2022)
- [Sharing Knowledge in Multi-Task Deep Reinforcement Learning](https://mlsanity.com/paper/2401.09561/) (2024)
- [Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments](https://mlsanity.com/paper/2201.00042/) (2021)
- [Multi-Task Reinforcement Learning for Quadrotors](https://mlsanity.com/paper/2412.12442/) (2024)
- [A Learning-based Quadcopter Controller with Extreme Adaptation](https://mlsanity.com/paper/2409.12949/) (2024)
- [Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2311.01075/) (2023)
- [Task and Domain Adaptive Reinforcement Learning for Robot Control](https://mlsanity.com/paper/2404.18713/) (2024)

## Abstract (arXiv)

Quadcopter attitude control involves two tasks: smooth attitude tracking and aggressive stabilization from arbitrary states. Although both can be formulated as tracking problems, their distinct state spaces and control strategies complicate a unified reward function. We propose a multitask deep reinforcement learning framework that leverages parallel simulation with IsaacGym and a Graph Convolutional Network (GCN) policy to address both tasks effectively. Our multitask Soft Actor-Critic (SAC) approach achieves faster, more reliable learning and higher sample efficiency than single-task methods. We validate its real-world applicability by deploying the learned policy - a compact two-layer network with 24 neurons per layer - on a Pixhawk flight controller, achieving 400 Hz control without extra computational resources. We provide our code at https://github.com/robot-perception-group/GraphMTSACUAV/.