Similarity-based Knowledge Transfer for Cross-Domain Reinforcement Learning

2023-12-05 · Sergio A. Serrano, Jose Martinez-Carranza, L. Enrique Sucar

Transferring knowledge in cross-domain reinforcement learning is a challenging setting in which learning is accelerated by reusing knowledge from a task with different observation and/or action space. However, it is often necessary to carefully select the source of knowledge for the receiving end to benefit from the transfer process. In this article, we study how to measure the similarity between cross-domain reinforcement learning tasks to select a source of knowledge that will improve the performance of the learning agent. We developed a semi-supervised alignment loss to match different spaces with a set of encoder-decoders, and use them to measure similarity and transfer policies across tasks. In comparison to prior works, our method does not require data to be aligned, paired or collected by expert policies. Experimental results, on a set of varied Mujoco control tasks, show the robustness of our method in effectively selecting and transferring knowledge, without the supervision of a tailored set of source tasks.

📄 PDF Abstract BibTeX arXiv:2312.03764

Code (0)

등록된 구현이 없습니다.

Tasks

MuJoCoreinforcement-learning Reinforcement Learning Transfer Learning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Transfer Reinforcement Learning for Differing Action Spaces via Q-Network Representations

2022-02-05 · Nathan Beck, Abhiramon Rajasekharan, Hieu Tran

Transfer learning approaches in reinforcement learning aim to assist agents in learning their target domains by leveraging the knowledge learned from other agents that have been trained on similar source domains. For exa…

Acrobot reinforcement-learning Reinforcement Learning (RL)Transfer Learning+1

FAST: Similarity-based Knowledge Transfer for Efficient Policy Learning

2025-07-27 · Alessandro Capurso, Elia Piccoli, Davide Bacciu arxiv

Transfer Learning (TL) offers the potential to accelerate learning by transferring knowledge across tasks. However, it faces critical challenges such as negative transfer, domain adaptation and inefficiency in selecting …

Transfer Learning Domain Adaptation

Knowledge Transfer for Cross-Domain Reinforcement Learning: A Systematic Review

2024-04-26 · Sergio A. Serrano, Jose Martinez-Carranza, L. Enrique Sucar

Reinforcement Learning (RL) provides a framework in which agents can be trained, via trial and error, to solve complex decision-making problems. Learning with little supervision causes RL methods to require large amounts…

Decision Making reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

Target-Aligned Bellman Backup for Cross-domain Offline Reinforcement Learning

2026-05-21 · Wei Liu, Ting Long arxiv

Cross-domain offline reinforcement learning (CDRL) aims to improve policy learning in a target domain by leveraging data collected from a source domain. Existing works typically assess the transferability of source-domai…

Reinforcement Learning Offline RL

Network Slicing via Transfer Learning aided Distributed Deep Reinforcement Learning

2023-01-09 · Tianlun Hu, Qi Liao, Qiang Liu, Georg Carle

Deep reinforcement learning (DRL) has been increasingly employed to handle the dynamic and complex resource management in network slicing. The deployment of DRL policies in real networks, however, is complicated by heter…

Deep Reinforcement Learning Management reinforcement-learning Reinforcement Learning+2