By the same authors

Clyde: A deep reinforcement learning DOOM playing agent

Research output: Chapter in Book/Report/Conference proceedingChapter (peer-reviewed)

Author(s)

Department/unit(s)

Publication details

Title of host publicationWhat's Next For AI In Games
DatePublished - 4 Feb 2017
Original languageEnglish

Abstract

In this paper we present the use of deep reinforcement learn-ing techniques in the context of playing partially observablemulti-agent 3D games. These techniques have traditionallybeen applied to fully observable 2D environments, or navigation tasks in 3D environments. We show the performanceof Clyde in comparison to other competitors within the con-text of the ViZDOOM competition that saw 9 bots competeagainst each other in DOOM death matches. Clyde managedto achieve 3rd place in the ViZDOOM competition held at theIEEE Conference on Computational Intelligence and Games2016. Clyde performed very well considering its relative sim-plicity and the fact that we deliberately avoided a high levelof customisation to keep the algorithm generic.

Discover related content

Find related publications, people, projects, datasets and more using interactive charts.

View graph of relations