Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments

TL;DR

This paper introduces ALP-GMM, a teacher algorithm that learns to generate effective curricula for Deep RL in parameterized environments by modeling learning progress with Gaussian mixtures, improving training efficiency.

Contribution

It proposes a novel ALP-GMM algorithm that models absolute learning progress to optimize environment sampling for curriculum learning in Deep RL.

Findings

ALP-GMM effectively personalizes curricula for different learners.

The approach is robust to varying ratios of learnable and unlearnable environments.

It scales well to high-dimensional, non-linear parameter spaces.

Abstract

We consider the problem of how a teacher algorithm can enable an unknown Deep Reinforcement Learning (DRL) student to become good at a skill over a wide range of diverse environments. To do so, we study how a teacher algorithm can learn to generate a learning curriculum, whereby it sequentially samples parameters controlling a stochastic procedural generation of environments. Because it does not initially know the capacities of its student, a key challenge for the teacher is to discover which environments are easy, difficult or unlearnable, and in what order to propose them to maximize the efficiency of learning over the learnable ones. To achieve this, this problem is transformed into a surrogate continuous bandit problem where the teacher samples environments in order to maximize absolute learning progress of its student. We present a new algorithm modeling absolute learning progress with Gaussian mixture models (ALP-GMM). We also adapt existing algorithms and provide a complete study in the context of DRL. Using parameterized variants of the BipedalWalker environment, we study their efficiency to personalize a learning curriculum for different learners (embodiments), their robustness to the ratio of learnable/unlearnable environments, and their scalability to non-linear and high-dimensional parameter spaces. Videos and code are available at https://github.com/flowersteam/teachDeepRL.