Similarity-based Knowledge Transfer For Cross-domain Reinforcement Learning

Abstract

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

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyserrano2023similarity

Related papers

• Contextual Policy Transfer In Reinforcement Learning Domains Via Deep Mixtures-of-experts (2020)0.00
• Knowledge Transfer In Deep Reinforcement Learning Via An Rl-specific Gan-based Correspondence Function (2022)2.26
• Zero-shot Cross-modal Transfer Of Reinforcement Learning Policies Through A Global Workspace (2024)0.00
• Improved Reinforcement Learning In Cooperative Multi-agent Environments Using Knowledge Transfer (2021)0.00
• Knowledge Transfer In Multi-task Deep Reinforcement Learning For Continuous Control (2020)0.00
• Learning Transferable Domain Priors For Safe Exploration In Reinforcement Learning (2019)0.00
• Transfer Reinforcement Learning In Heterogeneous Action Spaces Using Subgoal Mapping (2024)0.00
• Exploration In Knowledge Transfer Utilizing Reinforcement Learning (2024)0.00