Robot Manipulation Learning Using Generative Adversarial Imitation Learning

摘要

Imitation learning allows learning complex behaviors given demonstrations. Early approaches belonging to either Behavior Cloning or Inverse Reinforcement Learning were however of limited scalability to complex environments. A more promising approach termed as Generative Adversarial Imitation Learning tackles the imitation learning problem by drawing a connection with Generative Adversarial Networks. In this work, we advocate the use of this class of methods and investigate possible extensions by endowing them with global temporal consistency, in particular through a contrastive learning based approach.