Vision is well-known for its use in manipulation, especially using visual servoing. Due to the 3D nature of the world, using multiple camera views and merging them creates better representations for Q-learning and in turn, trains more sample efficient policies. Nevertheless, these multi-view policies are sensitive to failing cameras and can be burdensome to deploy. To mitigate these issues, we introduce a Merge And Disentanglement (MAD) algorithm that efficiently merges views to increase sample efficiency while simultaneously disentangling views by augmenting multi-view feature inputs with single-view features. This produces robust policies and allows lightweight deployment. We demonstrate the efficiency and robustness of our approach using Meta-World and ManiSkill3. For project website and code, see https://aalmuzairee.github.io/mad
@article{arxiv.2505.04619,
title = {Merging and Disentangling Views in Visual Reinforcement Learning for Robotic Manipulation},
author = {Abdulaziz Almuzairee and Rohan Patil and Dwait Bhatt and Henrik I. Christensen},
journal= {arXiv preprint arXiv:2505.04619},
year = {2025}
}
Comments
Accepted at CoRL 2025. For project website and code, see https://aalmuzairee.github.io/mad