paper-with-me

홈 › Papers

Sustainable Transfer Learning for Adaptive Robot Skills

2026-04-08 · Khalil Abuibaid, Vinit Hegiste, Nigora Gafur, Achim Wagner, Martin Ruskowski arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.06943

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningTransfer Learning

Similar Papers 제목 키워드 기반

Cloud-Based Hierarchical Imitation Learning for Scalable Transfer of Construction Skills from Human Workers to Assisting Robots

2023-09-20 · Hongrui Yu, Vineet R. Kamat, Carol C. Menassa

Assigning repetitive and physically-demanding construction tasks to robots can alleviate human workers's exposure to occupational injuries. Transferring necessary dexterous and adaptive artisanal construction craft skill…

Imitation LearningMotion Planning

Scaling simulation-to-real transfer by learning composable robot skills

2018-09-26 · Ryan Julian, Eric Heiden, Zhanpeng He, Hejia Zhang 외

We present a novel solution to the problem of simulation-to-real transfer, which builds on recent advances in robot skill decomposition. Rather than focusing on minimizing the simulation-reality gap, we learn a set of di…

Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning

2017-03-08 · Abhishek Gupta, Coline Devin, Yuxuan Liu, Pieter Abbeel 외

People can learn a wide range of tasks from their own experience, but can also learn from observing other creatures. This can accelerate acquisition of new skills even when the observed agent differs substantially from t…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Transfer Learning

A Simple Approach to Continual Learning by Transferring Skill Parameters

2021-10-19 · K. R. Zentner, Ryan Julian, Ujjwal Puri, Yulun Zhang 외

In order to be effective general purpose machines in real world environments, robots not only will need to adapt their existing manipulation skills to new circumstances, they will need to acquire entirely new skills on-t…

Continual Learning

HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videos

2026-02-02 · Yinhuai Wang, Qihan Zhao, Yuen Fui Lau, Runyi Yu 외 arxiv

Enabling humanoid robots to perform agile and adaptive interactive tasks has long been a core challenge in robotics. Current approaches are bottlenecked by either the scarcity of realistic interaction data or the need fo…

Data Augmentation