Keywords: Image-based RL, Data augmentation in RL, Continuous Control
Abstract: We present DrQ-v2, a model-free reinforcement learning (RL) algorithm for visual continuous control. DrQ-v2 builds on DrQ, an off-policy actor-critic approach that uses data augmentation to learn directly from pixels. We introduce several improvements that yield state-of-the-art results on the DeepMind Control Suite. Notably, DrQ-v2 is able to solve complex humanoid locomotion tasks directly from pixel observations, previously unattained by model-free RL. DrQ-v2 is conceptually simple, easy to implement, and provides significantly better computational footprint compared to prior work, with the majority of tasks taking just 8 hours to train on a single GPU. Finally, we publicly release DrQ-v2 's implementation to provide RL practitioners with a strong and computationally efficient baseline.
One-sentence Summary: We proposed a model-free off-policy algorithm for image-based continuous control that significantly outperforms previous methods both in sample and time complexity.
Supplementary Material: zip