Constraining the Size Growth of the Task Space with Socially Guided Intrinsic Motivation using Demonstrations

TL;DR

This paper introduces SGIM-D, an algorithm that combines social learning and intrinsic motivation to efficiently learn diverse skills with reduced reliance on teachers, demonstrated through a fishing skill experiment.

Contribution

The paper proposes a novel algorithm that integrates social guidance and intrinsic motivation for skill learning, reducing dependence on demonstrations.

Findings

SGIM-D effectively learns a wide range of skills.

The approach reduces the need for extensive demonstrations.

Successful application to a fishing skill learning task.

Abstract

This paper presents an algorithm for learning a highly redundant inverse model in continuous and non-preset environments. Our Socially Guided Intrinsic Motivation by Demonstrations (SGIM-D) algorithm combines the advantages of both social learning and intrinsic motivation, to specialise in a wide range of skills, while lessening its dependence on the teacher. SGIM-D is evaluated on a fishing skill learning experiment.