Learning to Play General Video-Games via an Object Embedding Network

William Woof, Ke Chen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

141 Downloads (Pure)

Abstract

Deep reinforcement learning (DRL) has proven to be an effective tool for creating general video-game AI. However most current DRL video-game agents learn end-to-end from the video-output of the game, which is superfluous for many applications and creates a number of additional problems. More importantly, directly working on pixel-based raw video data is substantially distinct from what a human player does. In this paper, we present a novel method which enables DRL agents to learn directly from object information. This is obtained via use of an object embedding network (OEN) that compresses a set of object feature vectors of different lengths into a single fixed-length unified feature vector representing the current game-state and fulfills the DRL simultaneously. We evaluate our OEN-based DRL agent by comparing to several state-of-the-art approaches on a selection of games from the GVG-AI Competition. Experimental results suggest that our object-based DRL agent yields performance comparable to that of those approaches used in our comparative study.

Original languageEnglish
Title of host publicationProceedings of the 2018 IEEE Conference on Computational Intelligence and Games, CIG 2018
PublisherIEEE Computer Society
Volume2018-August
ISBN (Electronic)9781538643594
DOIs
Publication statusPublished - 2018
Event14th IEEE Conference on Computational Intelligence and Games, CIG 2018 - Maastricht, Netherlands
Duration: 14 Aug 201817 Aug 2018

Conference

Conference14th IEEE Conference on Computational Intelligence and Games, CIG 2018
Country/TerritoryNetherlands
CityMaastricht
Period14/08/1817/08/18

Keywords

  • Artificial neural networks
  • Computer games
  • Deep Q-learning
  • General video game AI
  • Reinforcement learning

Fingerprint

Dive into the research topics of 'Learning to Play General Video-Games via an Object Embedding Network'. Together they form a unique fingerprint.

Cite this