Generative predecessor models for sample-efficient imitation learning

Abstract

We propose Generative Predecessor Models for Imitation Learning (GPRIL), a novel imitation learning algorithm that matches the state-action distribution to the distribution observed in expert demonstrations, using generative models to reason probabilistically about alternative histories of demonstrated states. We show that this approach allows an agent to learn robust policies using only a small number of expert demonstrations and self-supervised interactions with the environment. We derive this approach from first principles and compare it empirically to a state-of-the-art imitation learning method, showing that it outperforms or matches its performance on two simulated robot manipulation tasks and demonstrate significantly higher sample efficiency by applying the algorithm on a real robot.

Cited by in corpus (7)

• Goal-conditioned Imitation Learning
• Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling
• Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning
• VILD: Variational Imitation Learning with Diverse-quality Demonstrations
• Learning Retrospective Knowledge with Reverse Reinforcement Learning
• Forethought and Hindsight in Credit Assignment
• Support-weighted Adversarial Imitation Learning