When Should We Prefer State-to-Visual DAgger Over Visual Reinforcement Learning?
This work provides practical recommendations for practitioners in visual policy learning, though it is incremental as it compares existing methods without introducing new techniques.
This study empirically compares State-to-Visual DAgger and Visual Reinforcement Learning across 16 tasks from three benchmarks, finding that State-to-Visual DAgger does not universally outperform Visual RL but shows significant advantages in challenging tasks with more consistent performance, while its benefits in sample efficiency are less pronounced.
Learning policies from high-dimensional visual inputs, such as pixels and point clouds, is crucial in various applications. Visual reinforcement learning is a promising approach that directly trains policies from visual observations, although it faces challenges in sample efficiency and computational costs. This study conducts an empirical comparison of State-to-Visual DAgger, a two-stage framework that initially trains a state policy before adopting online imitation to learn a visual policy, and Visual RL across a diverse set of tasks. We evaluate both methods across 16 tasks from three benchmarks, focusing on their asymptotic performance, sample efficiency, and computational costs. Surprisingly, our findings reveal that State-to-Visual DAgger does not universally outperform Visual RL but shows significant advantages in challenging tasks, offering more consistent performance. In contrast, its benefits in sample efficiency are less pronounced, although it often reduces the overall wall-clock time required for training. Based on our findings, we provide recommendations for practitioners and hope that our results contribute valuable perspectives for future research in visual policy learning.