Meta Automatic Curriculum Learning

TL;DR

This paper introduces Meta-ACL, a novel approach to automatic curriculum learning that generalizes across different RL learners, improving training efficiency in diverse, procedurally generated environments.

Contribution

It formalizes Meta-ACL for black-box RL learners and presents AGAIN, the first implementation demonstrating its advantages over traditional ACL methods.

Findings

Meta-ACL outperforms classical ACL in diverse environments.

AGAIN effectively adapts curriculum generation across different learners.

Procedurally generated parkour environments validate the approach.

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 task spaces, 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 to an (unknown) distribution of learners. In this work, we present AGAIN, a first instantiation of Meta-ACL, and showcase its benefits for curriculum generation over classical ACL in multiple simulated environments including procedurally generated parkour environments with learners of varying morphologies. Videos and code are available at https://sites.google.com/view/meta-acl .