Deep Reinforcement Learning to Play StarCraft

Re:Deep Reinforcement Learning to Play StarCraft by whorleater on Wednesday September 14, 2016 @01:00PM (#12498974)

SC1 is not a weak point, it's generally considered to be better balanced, and is the "gold standard" for RTS's. SC1 also has far more training dataset than SC2.

[ Parent | on HN ]

Re:Deep Reinforcement Learning to Play StarCraft by ufo on Wednesday September 14, 2016 @03:08PM (#12500253)

In addition to the training data, there is also the BWAPI project, that lets the bots play the game against other bots or humans.

http://bwapi.github.io/

There isn't something similar available for SC2 due to a mix of technical and nontechnical issues:

https://github.com/bwapi/bwapi/wiki/FAQ#will-there-be-an-api...

[ Parent | on HN ]

Re:Deep Reinforcement Learning to Play StarCraft by whorleater on Wednesday September 14, 2016 @03:17PM (#12500329)

Yep! But as someone that built something on top of the BW API, I'd wager anyone going after SC1 AI to probably write their own thing. It's still an amazing API for general heuristics and modeling, but there's a few issues with it that stand in the way of making it a scaleable foundation.

[ Parent | on HN ]

Re:Deep Reinforcement Learning to Play StarCraft by ktRolster on Wednesday September 14, 2016 @06:57PM (#12501925)

What is wrong with it?

[ Parent | on HN ]