arXiv Machine Learning August 21, 2026 By Raphael Trumpp, \"Omer Veysel \c{C}a\u{g}atan, Bar{\i}\c{s} Akg\"un, Marco Caccamo

Higher Resolution, Better Generalization: Unlocking Visual Scaling in Deep Reinforcement Learning

Read the original on arXiv Machine Learning →

arXiv:2605. 10546v2 Announce Type: replace Abstract: Pixel-based deep reinforcement learning agents are typically trained on heavily downsampled visual observations, a convention inherited from early benchmarks rather than grounded in principled design.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Sep 22

Streaming Deep Reinforcement Learning Finally Works

arXiv:2410.14606v3 Announce Type: replace Abstract: Learning from a stream of experience as it arrives, also known as streaming learning, is a core part of natural learning. However, reliable streami...

By Mohamed Elsayed, Elena Sorina Lupu, Gautham Vasan, A. Rupam Mahmood

reinforcement-learning robotics benchmarks

arXiv AI

Jun 30

Learning to Adaptively Allocate Gaussians for Arbitrary-Scale Image Super-Resolution

arXiv:2606. 29400v1 Announce Type: cross Abstract: In computer graphics, visual content is continuously warped, zoomed and resampled.

By Giulio Federico, Giuseppe Amato, Claudio Gennaro, Fabio Carrara, Marco Di Benedetto

diffusion efficiency multimodal benchmarks

arXiv AI

2d ago

DeepJEPA: Scaling World Models from Within

DeepJEPA is a weight‑tied joint‑embedding predictive world model that treats transition depth as an inner test‑time scaling axis, learning when additional recurrent updates are worthwhile for each candidate and rollout step. Unlike traditional planners that uniformly deepen every transition, DeepJEPA concentrates extra computation on decision‑critical events such as contact onset and sustained object interaction, achieving comparable or better performance with only 1.00–1.26 updates per transition across five visual‑control settings. The approach demonstrates that improved planning does not require uniformly better object‑state decodability, but rather targeted internal computation where it can alter the planner’s elite set and action selection.

By Zijian Jin, Yunbei Zhang, Yuanzhe Liu, Ming Liu, Baian Chen, Weirui Ye, Shilong Liu, Marco Pavone

rag

arXiv Machine Learning

Aug 11

V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control

arXiv:2608. 07870v1 Announce Type: new Abstract: Improving sample efficiency remains a core challenge in reinforcement learning (RL), especially in real-world settings like robotics, where data collection is costly.

By Donghu Kim, Youngdo Lee, Hojoon Lee, Johan Obando-Ceron, Byungkun Lee, Aaron Courville, Pablo Samuel Castro, Jaegul Choo, Clare Lyle

reinforcement-learning robotics benchmarks

arXiv Machine Learning

Sep 22

Scaling Sim-to-Real VLA Reinforcement Learning with Generative 3D Worlds

arXiv:2603.18532v3 Announce Type: replace-cross Abstract: The strong performance of large vision-language models (VLMs) trained with reinforcement learning (RL) has motivated similar approaches for f...

By Andrew Choi, Xinjie Wang, Zhizhong Su, Wei Xu

llms reinforcement-learning robotics fine-tuning multimodal benchmarks

arXiv AI

Jul 2

KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning

arXiv:2601. 14232v2 Announce Type: replace-cross Abstract: Pixel-based reinforcement learning agents often fail under purely visual distribution shift even when latent dynamics and rewards are unchanged, but existing benchmarks entangle multiple sources of shift and hinder systematic analysis.

By Egor Cherepanov, Daniil Zelezetsky, Alexey K. Kovalev, Aleksandr I. Panov

agents reinforcement-learning benchmarks

One email a morning, machine-written

Related stories

Streaming Deep Reinforcement Learning Finally Works

Learning to Adaptively Allocate Gaussians for Arbitrary-Scale Image Super-Resolution

DeepJEPA: Scaling World Models from Within

V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control

Scaling Sim-to-Real VLA Reinforcement Learning with Generative 3D Worlds

KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning