Saved in:
Bibliographic Details
Main Authors: He, Bowen, Dong, Juncheng, Lin, Lin, Cheng, Xiang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.09727
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911669890842624
author He, Bowen
Dong, Juncheng
Lin, Lin
Cheng, Xiang
author_facet He, Bowen
Dong, Juncheng
Lin, Lin
Cheng, Xiang
contents A central challenge in reinforcement learning (RL) is to learn models that generalize beyond the tasks on which they are trained, a goal traditionally pursued through multi-task and meta RL. Recently, transformer architectures have emerged as a promising approach, enabling adaptation to new tasks via in-context learning without explicit parameter updates. From a functional perspective, a transformer can be viewed as a functional operator that maps a context to a task-specific function. It is thus fundamental to understand and design this operator to support stronger generalization in RL. In this work, we address this resulting question of generalization from a kernel-based perspective by establishing a connection between non-linear transformers and kernel-based temporal difference learning. By interpreting the transformer as performing regression in a Reproducing Kernel Hilbert Space (RKHS), we show that value functions from different domains can be represented using a shared set of weights, provided they lie within the same RKHS. Experiments on multiple MetaWorld domains support this interpretation, demonstrating convergence of the temporal-difference objective.
format Preprint
id arxiv_https___arxiv_org_abs_2605_09727
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle One for All: A Non-Linear Transformer can Enable Cross-Domain Generalization for In-Context Reinforcement Learning
He, Bowen
Dong, Juncheng
Lin, Lin
Cheng, Xiang
Machine Learning
Artificial Intelligence
A central challenge in reinforcement learning (RL) is to learn models that generalize beyond the tasks on which they are trained, a goal traditionally pursued through multi-task and meta RL. Recently, transformer architectures have emerged as a promising approach, enabling adaptation to new tasks via in-context learning without explicit parameter updates. From a functional perspective, a transformer can be viewed as a functional operator that maps a context to a task-specific function. It is thus fundamental to understand and design this operator to support stronger generalization in RL. In this work, we address this resulting question of generalization from a kernel-based perspective by establishing a connection between non-linear transformers and kernel-based temporal difference learning. By interpreting the transformer as performing regression in a Reproducing Kernel Hilbert Space (RKHS), we show that value functions from different domains can be represented using a shared set of weights, provided they lie within the same RKHS. Experiments on multiple MetaWorld domains support this interpretation, demonstrating convergence of the temporal-difference objective.
title One for All: A Non-Linear Transformer can Enable Cross-Domain Generalization for In-Context Reinforcement Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2605.09727