Don’t Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement Learning

One of the key challenges in visual Reinforcement Learning (RL) is to learn policies that can generalize to unseen environments. Recently, data augmentation techniques aiming at enhancing data diversity have demonstrated proven performance in improving the generalization ability of learned policies. However, due to the sensitivity of RL training, naively applying data augmentation, which transforms each pixel in a task-agnostic manner, may suffer from instability and damage the sample efficiency, thus further exacerbating the generalization performance. At the heart of this phenomenon is the diverged action distribution and high-variance value estimation in the face of augmented images. To alleviate this issue, we propose Task-aware Lipschitz Data Augmentation (TLDA) for visual RL, which explicitly identifies the task-correlated pixels with large Lipschitz constants, and only augments the task-irrelevant pixels for stability. We verify the effectiveness of our approach on DeepMind Control suite, CARLA and DeepMind Manipulation tasks. The extensive empirical results show that TLDA improves both sample efficiency and generalization; it outperforms previous state-of-the-art methods across 3 different visual control benchmarks.

Authors

• Zhecheng Yuan
• Guozheng Ma
• Yao Mu
• Bo Xia Tsinghua Shenzhen International Graduate School, Tsinghua University
• Bo Yuan University of Queensland
• Xueqian Wang Tsinghua Shenzhen International Graduate School, Tsinghua University
• Ping Luo The University of Hong Kong
• Huazhe Xu

Keywords

• Machine Learning: Deep Reinforcement Learning
• Machine Learning: Reinforcement Learning
• Robotics: Learning in Robotics