Ratcliffe, Dino, Devlin, Sam orcid.org/0000-0002-7769-3090, Kruschwitz, Udo et al. (1 more author) (2017) Clyde: A deep reinforcement learning DOOM playing agent. In: What's Next For AI In Games.
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.
Metadata
Item Type: | Book Section |
---|---|
Authors/Creators: |
|
Dates: |
|
Institution: | The University of York |
Academic Units: | The University of York > Faculty of Sciences (York) > Computer Science (York) |
Depositing User: | Pure (York) |
Date Deposited: | 07 Jul 2017 14:15 |
Last Modified: | 05 Jan 2025 00:43 |
Status: | Published |
Refereed: | Yes |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:118807 |
Download
Filename: Clyde_A_Deep_RL_Doom_Playing_Agent_Ratcliffe_Devlin_Kruschwitz_Citi.pdf
Description: Clyde - A Deep RL Doom Playing Agent - Ratcliffe, Devlin, Kruschwitz, Citi