From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data

Understand

While large-scale sequence modeling from offline data has led to impressive performance gains in natural language and image generation, directly translating such ideas to robotics has been challenging.

• One critical reason for this is that uncurated robot demonstration data, i.e.
• play data, collected from non-expert human demonstrators are often noisy, diverse, and distributionally multi-modal.
• This makes extracting useful, task-centric behaviors from such data a difficult generative modeling problem.