Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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

About

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.

Bram Grooten, Tristan Tomilin, Gautham Vasan, Matthew E. Taylor, A. Rupam Mahmood, Meng Fang, Mykola Pechenizkiy, Decebal Constantin Mocanu• 2023

Related benchmarks

TaskDatasetResultRank
Reinforcement LearningProcgen (test)
BigFish Return11.96
21
Visual Reinforcement LearningDMControl Cheetah Run
Episode Return432
16
Visual Reinforcement LearningDMControl Reacher Easy
Episode Return766
16
Visual Reinforcement LearningDMControl Walker Walk
Episode Return574
16
Visual Reinforcement LearningDMControl Ball in cup, Catch
Episode Return884
16
Visual Reinforcement LearningDMControl Finger, Spin
Episode Return810
16
Visual Reinforcement LearningDMControl Cartpole, Swingup
Episode Return704
16
Visual Reinforcement LearningDMControl Walker Run (test)
Environment Reward382
5
Visual Reinforcement LearningDMControl Pendulum, Swingup (test)
Episode Reward (ER)372
5
Visual Reinforcement LearningDMControl Hopper, Hop (test)
ER80
5
Showing 10 of 10 rows

Other info

Follow for update