Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning [article]

Denis Yarats, Rob Fergus, Alessandro Lazaric, Lerrel Pinto
2021 arXiv   pre-print
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
more » ... mplement, 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.
arXiv:2107.09645v1 fatcat:37obrkfuubc4fidzyy5d6xhzne