visual-rl

Tag

Cards List
#visual-rl

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

arXiv cs.LG · 2d ago Cached

This paper introduces V-Simba, a visual RL architecture that adds normalization layers and pointwise convolutions to improve sample efficiency and stability. It matches or outperforms state-of-the-art methods across DMC, Adroit, and Meta-World benchmarks while being more computationally efficient than DrQ-v2.

0 favorites 0 likes
← Back to home

Submit Feedback