Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Meta Automatic Curriculum Learning

Rémy Portelas 1 Clément Romac 1 Katja Hofmann 2 Pierre-Yves Oudeyer 1
1 Flowers - Flowing Epigenetic Robots and Systems
Inria Bordeaux - Sud-Ouest, U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
Abstract : A major challenge in the Deep RL (DRL) community is to train agents able to generalize their control policy over situations never seen in training. Training on diverse tasks has been identified as a key ingredient for good generalization,which pushed researchers towards using rich procedural task generation systems controlled through complex continuous parameter spaces. In such complex taskspaces, it is essential to rely on some form of Automatic Curriculum Learning(ACL) to adapt the task sampling distribution to a given learning agent, instead of randomly sampling tasks, as many could end up being either trivial or unfeasible.Since it is hard to get prior knowledge on such task spaces, many ACL algorithms explore the task space to detect progress niches over time, a costly tabula-rasa process that needs to be performed for each new learning agents, although they might have similarities in their capabilities profiles. To address this limitation, we introduce the concept of Meta-ACL, and formalize it in the context of black-box RL learners, i.e. algorithms seeking to generalize curriculum generation toan (unknown) distribution of learners. In this work, we present AGAIN, a first in-stantiation of Meta-ACL, and showcase its benefits for curriculum generation overclassical ACL in multiple simulated environments including procedurally generated parkour environments with learners of varying morphologies.
Document type :
Preprints, Working Papers, ...
Complete list of metadata
Contributor : Rémy Portelas Connect in order to contact the contributor
Submitted on : Monday, January 25, 2021 - 11:11:14 AM
Last modification on : Friday, December 3, 2021 - 11:34:07 AM
Long-term archiving on: : Monday, April 26, 2021 - 6:41:32 PM


Files produced by the author(s)


  • HAL Id : hal-03119914, version 1



Rémy Portelas, Clément Romac, Katja Hofmann, Pierre-Yves Oudeyer. Meta Automatic Curriculum Learning. 2021. ⟨hal-03119914⟩



Les métriques sont temporairement indisponibles