4 papers · 1 filter
Vision-Language Models Unlock Task-Centric Latent Actions
Alexander Nikulin, Ilya Zisman, Albina Klepach +5
Latent Action Models (LAMs) have rapidly gained traction as an important component in the pre-training pipelines of leading Vision-Language-Action models. However, they fail when o…
Yes, Q-learning Helps Offline In-Context RL
Denis Tarasov, Alexander Nikulin, Ilya Zisman +6
Existing offline in-context reinforcement learning (ICRL) methods have predominantly relied on supervised training objectives, which are known to have limitations in offline RL set…
Vintix: Action Model via In-Context Reinforcement Learning
Andrey Polubarov, Nikita Lyubaykin, Alexander Derevyagin +4
In-Context Reinforcement Learning (ICRL) represents a promising paradigm for developing generalist agents that learn at inference time through trial-and-error interactions, analogo…
N-Gram Induction Heads for In-Context RL: Improving Stability and Reducing Data Needs
Ilya Zisman, Alexander Nikulin, Viacheslav Sinii +5
In-context learning allows models like transformers to adapt to new tasks from a few examples without updating their weights, a desirable trait for reinforcement learning (RL). How…