تقرير
Towards Continual Reinforcement Learning for Quadruped Robots
| العنوان: | Towards Continual Reinforcement Learning for Quadruped Robots |
|---|---|
| المؤلفون: | Minelli, Giovanni, Vassiliades, Vassilis |
| سنة النشر: | 2023 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Robotics, Computer Science - Machine Learning |
| الوصف: | Quadruped robots have emerged as an evolving technology that currently leverages simulators to develop a robust controller capable of functioning in the real-world without the need for further training. However, since it is impossible to predict all possible real-world situations, our research explores the possibility of enabling them to continue learning even after their deployment. To this end, we designed two continual learning scenarios, sequentially training the robot on different environments while simultaneously evaluating its performance across all of them. Our approach sheds light on the extent of both forward and backward skill transfer, as well as the degree to which the robot might forget previously acquired skills. By addressing these factors, we hope to enhance the adaptability and performance of quadruped robots in real-world scenarios. Comment: 4 pages; Presented in the 3rd International Conference on Interactive Media, Smart Systems and Emerging Technologies (IMET) |
| نوع الوثيقة: | Working Paper |
| DOI: | 10.2312/imet.20231258 |
| URL الوصول: | http://arxiv.org/abs/2311.06828 |
| رقم الأكسشن: | edsarx.2311.06828 |
| قاعدة البيانات: | arXiv |
| DOI: | 10.2312/imet.20231258 |
|---|