Diffusion Meets DAgger: Supercharging Eye-in-hand Imitation Learning

arXiv:2402.17768v1 Announce Type: cross
Abstract: A common failure mode for policies trained with imitation is compounding execution errors at test time. When the learned policy encounters states that were not present in the expert demonstrations, the policy fails, leading to degenerate behavior. The Dataset Aggregation, or DAgger approach to this problem simply collects more data to cover these failure states. However, in practice, this is often prohibitively expensive. In this work, we propose Diffusion Meets DAgger (DMD), a method to …

abstract aggregation arxiv behavior cs.ai cs.cv cs.lg cs.ro dataset diffusion errors expert failure imitation learning policy test type