← Back to all news
arXiv AI By Egor Cherepanov, Daniil Zelezetsky, Alexey K. Kovalev, Aleksandr I. Panov

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

Read the original on arXiv AI →

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.

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 AI.

Related stories

arXiv Computer Vision
Sep 14

PAVXploreRL: Physical-Action-Visual World Model Reinforcement Learning with Action Exploration

PAVXploreRL introduces a reinforcement learning framework that builds on a pretrained latent world model to explicitly optimize Physical Plausibility, Action Adherence, and Visual Fidelity (PAV) objectives. By combining in‑distribution expert trajectories with noise‑driven out‑of‑distribution action exploration, the method avoids reliance on paired video supervision and improves generalization. Experiments demonstrate a 5.6% average performance gain over pretrained baselines and more reliable policy evaluation with reduced overestimation bias.

By Han Wang, Zijun Wang, Shuoshuo Xue, Rui Cao, Fengjiao Chen, Xiaodan Liang, Roy Ka-Wei Lee
reinforcement-learningroboticsbenchmarkssafety
More like this →
arXiv Machine Learning
Sep 7

Squint: Fast Visual Reinforcement Learning for Sim-to-Real Robotics

Squint is a visual Soft Actor Critic algorithm designed to accelerate reinforcement learning for robotics. It combines parallel simulation, a distributional critic, resolution squinting, layer normalization, a tuned update-to-data ratio, and an optimized implementation to reduce wall‑clock training time. On the SO‑101 Task Set, Squint trains policies in as little as 15 minutes on a single RTX 3090 GPU, with most tasks converging in under 6 minutes and successfully transferring to a real SO‑101 robot.

By Abdulaziz Almuzairee, Henrik I. Christensen
reinforcement-learningrobotics
More like this →
arXiv Computer Vision
Sep 7

Persistent Robot World Models: Stabilizing Multi-Step Rollouts via Reinforcement Learning

The paper introduces a reinforcement learning post‑training scheme that trains robot world models on their own autoregressive rollouts, using a contrastive RL objective adapted from diffusion models. It also proposes a training protocol that compares multiple variable‑length futures, a multi‑view visual fidelity reward, and demonstrates state‑of‑the‑art rollout fidelity on the DROID dataset, outperforming baselines on LPIPS, SSIM, and human preference tests.

By Jai Bardhan, Patrik Drozdik, Josef Sivic, Vladimir Petrik
diffusionreinforcement-learningroboticsbenchmarks
More like this →
arXiv Computer Vision
Sep 21

MintAct: A Unified Visual Agent for Digital Environments

arXiv:2609.22083v1 Announce Type: new Abstract: We present MintAct, a family of vision-language models that unifies UI grounding, multi-step navigation across mobile, desktop, and web, and visual too...

By Mingfei Gao, Rui Tian, Haiming Gang, Bohan Zhai, Le Zhang, Yuanzheng Gong, Di Feng, Ege \"Ozsoy, Kaixin Ma, Vishwesh Kirthivasan, O\u{g}uzhan Fatih Kar, Roman Bachmann, Anders Boesen Lindbo Larsen, Afshin Dehghan
llmsagentsreinforcement-learningmultimodalbenchmarks
More like this →