DiffClone: Enhanced Behaviour Cloning in Robotics with Diffusion-Driven Policy Learning

arXiv:2401.09243v2 Announce Type: replace-cross
Abstract: Robot learning tasks are extremely compute-intensive and hardware-specific. Thus the avenues of tackling these challenges, using a diverse dataset of offline demonstrations that can be used to train robot manipulation agents, is very appealing. The Train-Offline-Test-Online (TOTO) Benchmark provides a well-curated open-source dataset for offline training comprised mostly of expert data and also benchmark scores of the common offline-RL and behaviour cloning agents. In this paper, we introduce DiffClone, an offline algorithm of enhanced behaviour …

abstract agents arxiv benchmark challenges cloning compute cs.ai cs.lg cs.ro dataset diffusion diverse hardware manipulation offline policy robot robotics robot manipulation tasks test train type