Title

Transfer Learning Through Indirect Encoding

Keywords

Artificial neural networks; Generative and developmental systems; RoboCup soccer; Task transfer

Abstract

An important goal for the generative and developmental systems (GDS) community is to show that GDS approaches can compete with more mainstream approaches in machine learning (ML). One popular ML domain is RoboCup and its subtasks (e.g. Keepaway). This paper shows how a GDS approach called HyperNEAT competes with the best results to date in Keepaway. Furthermore, a significant advantage of GDS is shown to be in transfer learning. For example, playing Keepaway should contribute to learning the full game of soccer. Previous approaches to transfer have focused on transforming the original representation to fit the new task. In contrast, this paper explores transfer with a representation designed to be the same even across different tasks. A bird's eye view (BEV) representation is introduced that can represent different tasks on the same two-dimensional map. Yet the problem is that a raw two-dimensional map is high-dimensional and unstructured. The problem is addressed naturally by indirect encoding, which compresses the representation in HyperNEAT by exploiting its geometry. The result is that the BEV learns a Keepaway policy that transfers from two different training domains without further learning or manipulation. The results in this paper thus show the power of GDS versus other ML methods. Copyright 2010 ACM.

Publication Date

8-27-2010

Publication Title

Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10

Number of Pages

547-554

Document Type

Article; Proceedings Paper

Personal Identifier

scopus

DOI Link

https://doi.org/10.1145/1830483.1830587

Socpus ID

77955897298 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/77955897298

This document is currently not available here.

Share

COinS