Clyde: A deep reinforcement learning DOOM playing agent

Dino Ratcliffe, Sam Devlin, Udo Kruschwitz, Luca Citi

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

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.
Original languageEnglish
Title of host publicationWhat's Next For AI In Games
Subtitle of host publicationAAAI 2017 Workshop
Publication statusPublished - 4 Feb 2017

Cite this