Sustainable Transfer Learning for Adaptive Robot Skills
This addresses the challenge of sample efficiency and sustainability in robotic learning, though it is incremental as it builds on existing transfer learning methods.
The study tackled the problem of learning robot skills efficiently by investigating policy transfer across different robotic platforms for a peg-in-hole task, finding that fine-tuning significantly improves performance with fewer training time-steps compared to zero-shot transfer or training from scratch.
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.