Multi-Task Reinforcement Learning for Quadrotors

TL;DR

This paper introduces a multi-task reinforcement learning framework for quadrotors that improves sample efficiency and task versatility by sharing knowledge across diverse maneuvers, validated through simulation and real-world tests.

Contribution

The paper proposes a novel multi-task RL framework with shared dynamics, multi-critic architecture, and task encoders, enabling a single policy to perform multiple quadrotor tasks.

Findings

Outperforms baseline methods in sample efficiency

Achieves high performance across diverse tasks

Validated in both simulation and real-world environments

Abstract

Reinforcement learning (RL) has shown great effectiveness in quadrotor control, enabling specialized policies to develop even human-champion-level performance in single-task scenarios. However, these specialized policies often struggle with novel tasks, requiring a complete retraining of the policy from scratch. To address this limitation, this paper presents a novel multi-task reinforcement learning (MTRL) framework tailored for quadrotor control, leveraging the shared physical dynamics of the platform to enhance sample efficiency and task performance. By employing a multi-critic architecture and shared task encoders, our framework facilitates knowledge transfer across tasks, enabling a single policy to execute diverse maneuvers, including high-speed stabilization, velocity tracking, and autonomous racing. Our experimental results, validated both in simulation and real-world scenarios, demonstrate that our framework outperforms baseline approaches in terms of sample efficiency and overall task performance.