6 papers
KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning
Egor Cherepanov, Daniil Zelezetsky, Alexey K. Kovalev +1
Pixel-based reinforcement learning agents often fail under purely visual distribution shift even when latent dynamics and rewards are unchanged, but existing benchmarks entangle mu…
VLA: On Recurrent Memory for Partially Observable Manipulation in VLA Models
Egor Cherepanov, Nikita Kachaev, Daniil Zelezetsky +6
Vision-language-action (VLA) models predict chunks of future actions from the current observation, an assumption that fails under partial observability, where decisions depend on i…
Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization
Nikita Kachaev, Mikhail Kolosov, Daniil Zelezetsky +2
The growing success of Vision-Language-Action (VLA) models stems from the promise that pretrained Vision-Language Models (VLMs) can endow agents with transferable world knowledge a…
A New Perspective on Transformers in Online Reinforcement Learning for Continuous Control
Nikita Kachaev, Daniil Zelezetsky, Egor Cherepanov +2
Despite their effectiveness and popularity in offline or model-based reinforcement learning (RL), transformers remain underexplored in online model-free RL due to their sensitivity…
Accelerating Transformers in Online RL
Daniil Zelezetsky, Alexey K. Kovalev, Aleksandr I. Panov
The appearance of transformer-based models in Reinforcement Learning (RL) has expanded the horizons of possibilities in robotics tasks, but it has simultaneously brought a wide ran…
Re:Frame -- Retrieving Experience From Associative Memory
Daniil Zelezetsky, Egor Cherepanov, Alexey K. Kovalev +1
Offline reinforcement learning (RL) often deals with suboptimal data when collecting large expert datasets is unavailable or impractical. This limitation makes it difficult for age…