Reuse of Neural Modules for General Video Game Playing release_t6267vxzezcsxfnja4sfneul54

by Alexander Braylan, Mark Hollenbeck, Elliot Meyerson, Risto Miikkulainen

Abstract

A general approach to knowledge transfer is introduced in which an agent controlled by a neural network adapts how it reuses existing networks as it learns in a new domain. Networks trained for a new domain can improve their performance by routing activation selectively through previously learned neural structure, regardless of how or for what it was learned. A neuroevolution implementation of this approach is presented with application to high-dimensional sequential decision-making domains. This approach is more general than previous approaches to neural transfer for reinforcement learning. It is domain-agnostic and requires no prior assumptions about the nature of task relatedness or mappings. The method is analyzed in a stochastic version of the Arcade Learning Environment, demonstrating that it improves performance in some of the more complex Atari 2600 games, and that the success of transfer can be predicted based on a high-level characterization of game dynamics.
In application/xml+jats format

Archived Files and Locations

application/pdf  876.5 kB
file_iyz6e6nkpvg2dg5lrelpskh5tu
ojs.aaai.org (publisher)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article-journal
Stage   published
Date   2016-02-21
Proceedings Metadata
Not in DOAJ
Not in Keepers Registry
ISSN-L:  2159-5399
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: b62b8505-0a52-430a-94d6-0ae730f2a7fb
API URL: JSON