News for hackers. Stuff that matters.

A comment on StarCraft Micromanagement with Reinforcement Learning and Curriculum Transfer. Parent comment

Re:StarCraft Micromanagement with Reinforcement Learning and... by taurath on Thursday April 19, 2018 @07:50PM (#16881149)
Just like playing against MarineKing would get stale quickly for most players :P

The problem with starcraft is that its like chess - for a lot of players it really DOES get stale pretty quickly, with only one or two interesting moments in a game (assuming no early blunders). The games that are interesting involve near perfect play for 10-20 minutes and then frequently one split second decision. Macro changes or new strategies are quickly picked up and interated on, and I think thats what the hardcore still stick around for

[ Parent | on HN ]
Re:StarCraft Micromanagement with Reinforcement Learning and... by loser777 on Thursday April 19, 2018 @07:55PM (#16881167)
The difference is that an interesting AI could likely be scaled back meaningfully for lower skill levels. Make MarineKing play with only the mouse against a lower skilled opponent? The results might be less stale.

Rate limiting a brute-force AI would make it trivially bad.

[ Parent | on HN ]
Re:StarCraft Micromanagement with Reinforcement Learning and... by acomar on Friday April 20, 2018 @12:07AM (#16882085)
Not really. Stopping MarineKing from sending tons of APM is only part of the challenge. His choices for what to do in any given frame (yes, frame) are also just better than basically every player on the ladder. If you remove his keyboard, you'll find that he still wins most games against folks who don't know the game.
[ Parent | on HN ]