Divide & Conquer Imitation Learning - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Divide & Conquer Imitation Learning

Résumé

When cast into the Deep Reinforcement Learning framework, many robotics tasks require solving a long horizon and sparse reward problem, where learning algorithms struggle. In such context, Imitation Learning (IL) can be a powerful approach to bootstrap the learning process. However, most IL methods require several expert demonstrations which can be prohibitively difficult to acquire. Only a handful of IL algorithms have shown efficiency in the context of an extreme low expert data regime where a single expert demonstration is available. In this paper, we present a novel algorithm designed to imitate complex robotic tasks from the states of an expert trajectory. Based on a sequential inductive bias, our method divides the complex task into smaller skills. The skills are learned into a goal-conditioned policy that is able to solve each skill individually and chain skills to solve the entire task. We show that our method imitates a non-holonomic navigation task and scales to a complex simulated robotic manipulation task with very high sample efficiency.
Fichier principal
Vignette du fichier
DCIL.pdf (5.09 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03753530 , version 1 (18-08-2022)

Identifiants

Citer

Alexandre Chenu, Nicolas Perrin-Gilbert, Olivier Sigaud. Divide & Conquer Imitation Learning. 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022), Oct 2022, Kyoto, Japan. pp.8630-8637, ⟨10.1109/IROS47612.2022.9982020⟩. ⟨hal-03753530⟩
77 Consultations
74 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More