Modular Architecture for StarCraft II with Deep Reinforcement Learning
We present a novel modular architecture for StarCraft II AI. The architecture splits responsibilities between multiple modules that each control one aspect of the game, such as build-order selection or tactics. A centralized scheduler reviews macros suggested by all modules and decides their order of execution. An updater keeps track of environment changes and instantiates macros into series of executable actions. Modules in this framework can be optimized independently or jointly via human design, planning, or reinforcement learning. We apply deep reinforcement learning techniques to training two out of six modules of a modular agent with self-play, achieving 94% or 87% win rates against the "Harder" (level 5) built-in Blizzard bot in Zerg vs. Zerg matches, with or without fog-of-war.
Authors

Are you an author of this paper? Check the Twitter handle we have for you is correct.

Dennis Lee (edit)
Haoran Tang (edit)
Jeffrey O Zhang (edit)
Huazhe Xu (add twitter)
Trevor Darrell (add twitter)
Pieter Abbeel (edit)
Ask The Authors

Ask the authors of this paper a question or leave a comment.

Read it. Rate it.
#1. Which part of the paper did you read?

#2. The paper contains new data or analyses that is openly accessible?
#3. The conclusion is supported by the data and analyses?
#4. The conclusion is of scientific interest?
#5. The result is likely to lead to future research?

Github
User:
None (add)
Repo:
None (add)
Stargazers:
0
Forks:
0
Open Issues:
0
Network:
0
Subscribers:
0
Language:
None
Youtube
Link:
None (add)
Views:
0
Likes:
0
Dislikes:
0
Favorites:
0
Comments:
0
Other
Sample Sizes (N=):
Inserted:
Words Total:
Words Unique:
Source:
Abstract:
None
11/08/18 06:01PM
5,285
2,043
Tweets
SciFi: Modular Architecture for StarCraft II with Deep Reinforcement Learning. https://t.co/65k4GhagFe
PerthMLGroup: RT @Miles_Brundage: "Modular Architecture for StarCraft II with Deep Reinforcement Learning," Lee and Tang et al.: https://t.co/QnQvgP3BzQ
AssistedEvolve: RT @Miles_Brundage: "Modular Architecture for StarCraft II with Deep Reinforcement Learning," Lee and Tang et al.: https://t.co/QnQvgP3BzQ
arxivml: "Modular Architecture for StarCraft II with Deep Reinforcement Learning", Dennis Lee, Haoran Tang, Jeffrey O Zhang,… https://t.co/PTdPlb2qxD
JeanMarcJAzzi: RT @Miles_Brundage: "Modular Architecture for StarCraft II with Deep Reinforcement Learning," Lee and Tang et al.: https://t.co/QnQvgP3BzQ
teenvan1995: RT @Miles_Brundage: "Modular Architecture for StarCraft II with Deep Reinforcement Learning," Lee and Tang et al.: https://t.co/QnQvgP3BzQ
polynomia26: DLでのスタクラ2AI https://t.co/tlO8cIOgtZ
akdm_bot: RT @Miles_Brundage: "Modular Architecture for StarCraft II with Deep Reinforcement Learning," Lee and Tang et al.: https://t.co/QnQvgP3BzQ
KouroshMeshgi: RT @Miles_Brundage: "Modular Architecture for StarCraft II with Deep Reinforcement Learning," Lee and Tang et al.: https://t.co/QnQvgP3BzQ
BrundageBot: Modular Architecture for StarCraft II with Deep Reinforcement Learning. Dennis Lee, Haoran Tang, Jeffrey O Zhang, Huazhe Xu, Trevor Darrell, and Pieter Abbeel https://t.co/2naPoOMs2I
mnrmja007: RT @Miles_Brundage: "Modular Architecture for StarCraft II with Deep Reinforcement Learning," Lee and Tang et al.: https://t.co/QnQvgP3BzQ
Miles_Brundage: "Modular Architecture for StarCraft II with Deep Reinforcement Learning," Lee and Tang et al.: https://t.co/QnQvgP3BzQ
Images
Related