Learning robot skills from scratch is often time-consuming, while reusing data promotes sustainability and improves sample efficiency. This study investigates policy transfer across different robotic platforms, focusing on peg-in-hole task using reinforcement learning (RL). Policy training is carried out on two different robots. Their policies are transferred and evaluated for zero-shot, fine-tuning, and training from scratch. Results indicate that zero-shot transfer leads to lower success rates and relatively longer task execution times, while fine-tuning significantly improves performance with fewer training time-steps. These findings highlight that policy transfer with adaptation techniques improves sample efficiency and generalization, reducing the need for extensive retraining and supporting sustainable robotic learning.
@article{arxiv.2604.06943,
title = {Sustainable Transfer Learning for Adaptive Robot Skills},
author = {Khalil Abuibaid and Vinit Hegiste and Nigora Gafur and Achim Wagner and Martin Ruskowski},
journal= {arXiv preprint arXiv:2604.06943},
year = {2026}
}
Comments
Published in RAAD 2025 (Springer). 7 pages, 5 figures