Abstract:Reinforcement learning (RL) policies are typically trained for fixed objectives, making reuse difficult when task requirements change. We study inference-time policy reuse: given a library of pre-trained policies and a new composite objective, can a high-quality policy be constructed entirely offline, without additional environment interaction? We introduce lever (Leveraging Efficient Vector Embeddings for Reusable policies), an end-to-end framework that retrieves relevant policies, evaluates them using behavioral embeddings, and composes new policies via offline Q-value composition. We focus on the support-limited regime, where no value propagation is possible, and show that the effectiveness of reuse depends critically on the coverage of available transitions. To balance performance and computational cost, lever proposes composition strategies that control the exploration of candidate policies. Experiments in deterministic GridWorld environments show that inference-time composition can match, and in some cases exceed, training-from-scratch performance while providing substantial speedups. At the same time, performance degrades when long-horizon dependencies require value propagation, highlighting a fundamental limitation of offline reuse.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2604.20174 [cs.LG] |
| (or arXiv:2604.20174v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.20174 arXiv-issued DOI via DataCite (pending registration) |
From: Noha Ibrahim [view email]
[v1]
Wed, 22 Apr 2026 04:28:45 UTC (1,914 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。