English

MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning

Machine Learning 2023-12-27 v1 Artificial Intelligence Computer Vision and Pattern Recognition Robotics

Abstract

The visual world provides an abundance of information, but many input pixels received by agents often contain distracting stimuli. Autonomous agents need the ability to distinguish useful information from task-irrelevant perceptions, enabling them to generalize to unseen environments with new distractions. Existing works approach this problem using data augmentation or large auxiliary networks with additional loss functions. We introduce MaDi, a novel algorithm that learns to mask distractions by the reward signal only. In MaDi, the conventional actor-critic structure of deep reinforcement learning agents is complemented by a small third sibling, the Masker. This lightweight neural network generates a mask to determine what the actor and critic will receive, such that they can focus on learning the task. The masks are created dynamically, depending on the current input. We run experiments on the DeepMind Control Generalization Benchmark, the Distracting Control Suite, and a real UR5 Robotic Arm. Our algorithm improves the agent's focus with useful masks, while its efficient Masker network only adds 0.2% more parameters to the original structure, in contrast to previous work. MaDi consistently achieves generalization results better than or competitive to state-of-the-art methods.

Keywords

Cite

@article{arxiv.2312.15339,
  title  = {MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning},
  author = {Bram Grooten and Tristan Tomilin and Gautham Vasan and Matthew E. Taylor and A. Rupam Mahmood and Meng Fang and Mykola Pechenizkiy and Decebal Constantin Mocanu},
  journal= {arXiv preprint arXiv:2312.15339},
  year   = {2023}
}

Comments

Accepted as full-paper (oral) at AAMAS 2024. Code is available at https://github.com/bramgrooten/mask-distractions and see our 40-second video at https://youtu.be/2oImF0h1k48

R2 v1 2026-06-28T14:00:50.097Z