Residual Reinforcement Learning from Demonstrations - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year : 2021

Residual Reinforcement Learning from Demonstrations

Abstract

Residual reinforcement learning (RL) has been proposed as a way to solve challenging robotic tasks by adapting control actions from a conventional feedback controller to maximize a reward signal. We extend the residual formulation to learn from visual inputs and sparse rewards using demonstrations. Learning from images, proprioceptive inputs and a sparse task-completion reward relaxes the requirement of accessing full state features, such as object and target positions. In addition, replacing the base controller with a policy learned from demonstrations removes the dependency on a hand-engineered controller in favour of a dataset of demonstrations, which can be provided by non-experts. Our experimental evaluation on simulated manipulation tasks on a 6-DoF UR5 arm and a 28-DoF dexterous hand demonstrates that residual RL from demonstrations is able to generalize to unseen environment conditions more flexibly than either behavioral cloning or RL fine-tuning, and is capable of solving high-dimensional, sparse-reward tasks out of reach for RL from scratch.
Fichier principal
Vignette du fichier
RRLfD.pdf (2.28 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03260683 , version 1 (15-06-2021)

Identifiers

Cite

Minttu Alakuijala, Gabriel Dulac-Arnold, Julien Mairal, Jean Ponce, Cordelia Schmid. Residual Reinforcement Learning from Demonstrations. 2021. ⟨hal-03260683⟩
133 View
287 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More