[2604.05112] Vintix II: Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement Learner

Computer Science > Machine Learning arXiv:2604.05112 (cs) [Submitted on 6 Apr 2026] Title:Vintix II: Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement Learner Authors:Andrei Polubarov, Lyubaykin Nikita, Alexander Derevyagin, Artyom Grishin, Igor Saprygin, Aleksandr Serkov, Mark Averchenko, Daniil Tikhonov, Maksim Zhdanov, Alexander Nikulin, Ilya Zisman, Albina Klepach, Alexey Zemtsov, Vladislav Kurenkov View a PDF of the paper titled Vintix II: Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement Learner, by Andrei Polubarov and 13 other authors View PDF HTML (experimental) Abstract:Recent progress in in-context reinforcement learning (ICRL) has demonstrated its potential for training generalist agents that can acquire new tasks directly at inference. Algorithm Distillation (AD) pioneered this paradigm and was subsequently scaled to multi-domain settings, although its ability to generalize to unseen tasks remained limited. The Decision Pre-Trained Transformer (DPT) was introduced as an alternative, showing stronger in-context reinforcement learning abilities in simplified domains, but its scalability had not been established. In this work, we extend DPT to diverse multi-domain environments, applying Flow Matching as a natural training choice that preserves its interpretation as Bayesian posterior sampling. As a result, we obtain an agent trained across hundreds of diverse tasks that achieves clear gains in generalization to the held...