Implicit Offline Reinforcement Learning via Supervised Learning
This provides a more effective approach for robotic skill acquisition from offline data, though it is incremental as it extends existing supervised learning methods to implicit models.
The paper tackles the problem of learning robotic skills from fixed datasets in offline reinforcement learning by proposing implicit models that leverage return information, showing they match or outperform explicit algorithms on high-dimension manipulation and locomotion tasks.
Offline Reinforcement Learning (RL) via Supervised Learning is a simple and effective way to learn robotic skills from a dataset collected by policies of different expertise levels. It is as simple as supervised learning and Behavior Cloning (BC), but takes advantage of return information. On datasets collected by policies of similar expertise, implicit BC has been shown to match or outperform explicit BC. Despite the benefits of using implicit models to learn robotic skills via BC, offline RL via Supervised Learning algorithms have been limited to explicit models. We show how implicit models can leverage return information and match or outperform explicit algorithms to acquire robotic skills from fixed datasets. Furthermore, we show the close relationship between our implicit methods and other popular RL via Supervised Learning algorithms to provide a unified framework. Finally, we demonstrate the effectiveness of our method on high-dimension manipulation and locomotion tasks.