Auxiliary task discovery through generate-and-test

TL;DR

This paper presents a method for automatically discovering useful auxiliary tasks in reinforcement learning by continually generating and testing tasks based on their utility for the main task, improving learning efficiency.

Contribution

It introduces a novel generate-and-test approach for auxiliary task discovery and a new measure of task usefulness based on feature utility for the main task.

Findings

Our method outperforms random task selection in various environments.

Auxiliary tasks with high utility improve data efficiency.

The approach reduces the need for manual task design.

Abstract

In this paper, we explore an approach to auxiliary task discovery in reinforcement learning based on ideas from representation learning. Auxiliary tasks tend to improve data efficiency by forcing the agent to learn auxiliary prediction and control objectives in addition to the main task of maximizing reward, and thus producing better representations. Typically these tasks are designed by people. Meta-learning offers a promising avenue for automatic task discovery; however, these methods are computationally expensive and challenging to tune in practice. In this paper, we explore a complementary approach to the auxiliary task discovery: continually generating new auxiliary tasks and preserving only those with high utility. We also introduce a new measure of auxiliary tasks' usefulness based on how useful the features induced by them are for the main task. Our discovery algorithm significantly outperforms random tasks and learning without auxiliary tasks across a suite of environments.