Automatic Curriculum Learning For Deep RL: A Short Survey
It is an incremental survey that organizes existing literature for researchers in reinforcement learning.
This survey paper provides an introduction to Automatic Curriculum Learning (ACL) in Deep Reinforcement Learning, summarizing its applications in improving sample efficiency and performance, and aims to foster new ideas by presenting the current state of the art.
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. 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.