Automatic Curriculum Learning For Deep RL: A Short Survey - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Automatic Curriculum Learning For Deep RL: A Short Survey

Rémy Portelas
  • Function : Author
  • PersonId : 1058561
Cédric Colas
Lilian Weng
  • Function : Author
Pierre-Yves Oudeyer

Abstract

Automatic Curriculum Learning (ACL) has become a cornerstone of recent successes in Deep Reinforcement Learning (DRL). These methods shape the learning trajectories of agents by challenging them with tasks adapted to their capacities. In recent years, they have been used to improve sample efficiency and asymptotic performance, to organize exploration, to encourage generalization or to solve sparse reward problems, among others. To do so, ACL mechanisms can act on many aspects of learning problems. They can optimize domain randomization for Sim2Real transfer, organize task presentations in multi-task robotic settings, order sequences of opponents in multi-agent scenarios, etc. The ambition of this work is dual: 1) to present a compact and accessible introduction to the Automatic Curriculum Learning literature and 2) to draw a bigger picture of the current state of the art in ACL to encourage the cross-breeding of existing concepts and the emergence of new ideas.
Fichier principal
Vignette du fichier
acl-drl-survey.pdf (970.14 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02923635 , version 1 (27-08-2020)

Identifiers

  • HAL Id : hal-02923635 , version 1

Cite

Rémy Portelas, Cédric Colas, Lilian Weng, Katja Hofmann, Pierre-Yves Oudeyer. Automatic Curriculum Learning For Deep RL: A Short Survey. IJCAI 2020 - International Joint Conference on Artificial Intelligence, Jan 2021, Kyoto / Virtuelle, Japan. ⟨hal-02923635⟩

Collections

ENSTA INRIA INRIA2
241 View
226 Download

Share

Gmail Facebook X LinkedIn More