Vintix: Action Model via In-Context Reinforcement Learning
Andrei Polubarov, Lyubaykin Nikita, Alexander Derevyagin, Ilya Zisman, Denis Tarasov, Alexander Nikulin, Vladislav Kurenkov
Abstract
In-Context Reinforcement Learning (ICRL) represents a promising paradigm for developing generalist agents that learn at inference time through trial-and-error interactions, analogous to how large language models adapt contextually, but with a focus on reward maximization. However, the scalability of ICRL beyond toy tasks and single-domain settings remains an open challenge. In this work, we present the first steps toward scaling ICRL by introducing a fixed, cross-domain model capable of learning behaviors through in-context reinforcement learning. Our results demonstrate that Algorithm Distillation, a framework designed to facilitate ICRL, offers a compelling and competitive alternative to expert distillation to construct versatile action models. These findings highlight the potential of ICRL as a scalable approach for generalist decision-making systems.
BibTeX
@inproceedings{
polubarov2025vintix,
title={Vintix: Action Model via In-Context Reinforcement Learning},
author={Andrei Polubarov and Lyubaykin Nikita and Alexander Derevyagin and Ilya Zisman and Denis Tarasov and Alexander Nikulin and Vladislav Kurenkov},
booktitle={Forty-second International Conference on Machine Learning},
year={2025},
url={https://openreview.net/forum?id=gi9MOXNfw2}
}