Abstract
Multi-agent reinforcement learning has emerged as a promising approach for the control of multi-robot systems. Nevertheless, the low sample efficiency of MARL poses a significant obstacle to its broader application in robotics. While data augmentation appears to be a straightforward solution for improving sample efficiency, it usually incurs training instability, making the sample efficiency worse. Moreover, manually choosing suitable augmentations for a variety of tasks is a tedious and time-consuming process. To mitigate these challenges, our research theoretically analyzes the implications of data augmentation on MARL algorithms. Guided by these insights, we present AdaptAUG, an adaptive framework designed to selectively identify beneficial data augmentations, thereby achieving superior sample efficiency and overall performance in multi-robot tasks. Extensive experiments in both simulated and real-world multi-robot scenarios validate the effectiveness of our proposed framework.
Methods
This paper focuses on solving the following problem: How to choose appropriate augmentation methods to enhance the performance of MARL in a specific task? We introduce a general framework called Adaptive Data Augmentation (AdaptAUG) for selecting augmentation methods. The AdaptAUG framework is illustrated as below.
Contact
If you have any questions, please feel free to contact Xin Yu at nlsdeyuxin[at]buaa[dot]edu[dot]cn[dot].