The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixels
Robots have to face challenging perceptual settings, including changes in viewpoint, lighting, and background. Current simulated reinforcement learning (RL) benchmarks such as DM Control provide visual input without such complexity, which limits the transfer of well-performing methods to the real world. In this paper, we extend DM Control with three kinds of visual distractions (variations in background, color, and camera pose) to produce a new challenging benchmark for vision-based control, and we analyze state of the art RL algorithms in these settings. Our experiments show that current RL methods for vision-based control perform poorly under distractions, and that their performance decreases with increasing distraction complexity, showing that new methods are needed to cope with the visual complexities of the real world. We also find that combinations of multiple distraction types are more difficult than a mere combination of their individual effects.
Code (4)
Tasks
reinforcement-learningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
VIBR: Learning View-Invariant Value Functions for Robust Visual Control
End-to-end reinforcement learning on images showed significant progress in the recent years. Data-based approach leverage data augmentation and domain randomization while representation learning methods use auxiliary los…
Data AugmentationRepresentation LearningLearning Generalizable Representations for Reinforcement Learning via Adaptive Meta-learner of Behavioral Similarities
How to learn an effective reinforcement learning-based model for control tasks from high-level visual observations is a practical and challenging problem. A key to solving this problem is to learn low-dimensional state r…
Data Augmentationreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning
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…
Data AugmentationDeep Reinforcement LearningJoint Self-Supervised Learning for Vision-based Reinforcement Learning
Vision-based reinforcement learning requires efficient and robust representations of image-based observations, especially when the images contain distracting (task-irrelevant) elements such as shadows, clouds, and light.…
Autonomous Drivingcontinuous-controlContinuous Controlreinforcement-learning+3DEAR: Disentangled Environment and Agent Representations for Reinforcement Learning without Reconstruction
Reinforcement Learning (RL) algorithms can learn robotic control tasks from visual observations, but they often require a large amount of data, especially when the visual scene is complex and unstructured. In this paper,…
Reinforcement Learning (RL)