Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning
This provides a computationally efficient baseline for RL practitioners working on visual control tasks, though it is incremental over prior methods.
The authors tackled visual continuous control in reinforcement learning by developing DrQ-v2, an improved model-free algorithm that achieves state-of-the-art results on the DeepMind Control Suite, solving complex humanoid locomotion tasks from pixels and training in as little as 8 hours on a single GPU.
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.