Andrei Polubarov

Yes, Q-learning Helps Offline In-Context RL

Vision-Language Models Unlock Task-Centric Latent Actions

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

N-Gram Induction Heads for In-Context RL: Improving Stability and Reducing Data Needs

Vintix: Action Model via In-Context Reinforcement Learning

Latent Action Learning Requires Supervision in the Presence of Distractors