StarCraft Micromanagement with Reinforcement Learning and Curriculum Transfer • Hacker News Board

Re: StarCraft Micromanagement with Reinforcement Learning and Curriculum Transfer

#51

Post by littlestymaar » Fri, Apr 20, 2018, 1:27 PM UTC

vk23 wrote: post #47

littlestymaar wrote: post #43

Earlier quoted context omitted.

> like imperfect information The information is only imperfect for a human but an IA can have a way better access to information: - if you scout you opponent mineral line and click on the minerals, you know exactly how much minerals he's harvested since the beginning of the game. If you scout your opponent army and building, you know exactly how much he spent. Then you can deduce if he has something hidden somewhere…

> Then you can deduce if he has something hidden somewhere or in production. Of course this is impossible to do for a human, but really easy for a computer. This is definitly not impossible for humans. High level SC players are able to keep track of the mineral and gas spendings of their opponent in the early game (After the early game there is usually no complete information to calculate this). Just seeing the timin…

> The same thing was said about early chess AIs and the Alpha GO project

Afaik, chess AI (I mean, modern ones like deep blue) had little to no wide impact on AI. They had a lot of impact on chess though.

But it's way easier to model a chessboard than a game like StarCraft, the domain specific work is just orders of magnitude bigger.

Re: StarCraft Micromanagement with Reinforcement Learning and Curriculum Transfer

#52

Post by vk23 » Fri, Apr 20, 2018, 1:38 PM UTC

jon_richards wrote: post #50

vk23 wrote: post #47

Earlier quoted context omitted.

> Then you can deduce if he has something hidden somewhere or in production. Of course this is impossible to do for a human, but really easy for a computer. This is definitly not impossible for humans. High level SC players are able to keep track of the mineral and gas spendings of their opponent in the early game (After the early game there is usually no complete information to calculate this). Just seeing the timin…

At the top levels, it's a lot more about where those units/buildings are than whether they exist. You know they're going to be mining and spending efficiently, so just seeing the number of workers gives you a very good idea of how much other stuff they have. Pros also check to see what technologies are being researched (buildings have a different animation while researching). You can't get much more scouting than tha…

> You can't get much more scouting than that because there is a cost associated with scouting, either because you lose a worker's time or because you spread out your army.

I agree but I was mainly talking about the time it takes to perform the scouting. A AI could scout 5 different places at the same time which is pretty hard for a human to do without falling behind elsewhere. I know SC pros are really good at multitasking but at some point the AI is just superior. If this gives the AI a significant advantage is a different question.

Re: StarCraft Micromanagement with Reinforcement Learning and Curriculum Transfer

#53

Post by vk23 » Fri, Apr 20, 2018, 1:45 PM UTC

littlestymaar wrote: post #51

vk23 wrote: post #47

Earlier quoted context omitted.

> Then you can deduce if he has something hidden somewhere or in production. Of course this is impossible to do for a human, but really easy for a computer. This is definitly not impossible for humans. High level SC players are able to keep track of the mineral and gas spendings of their opponent in the early game (After the early game there is usually no complete information to calculate this). Just seeing the timin…

> The same thing was said about early chess AIs and the Alpha GO project Afaik, chess AI (I mean, modern ones like deep blue) had little to no wide impact on AI. They had a lot of impact on chess though. But it's way easier to model a chessboard than a game like StarCraft, the domain specific work is just orders of magnitude bigger.

> Afaik, chess AI (I mean, modern ones like deep blue) had little to no wide impact on AI.

Apart from the pure technical side (which I am no expert in so you might be right) the impact on public attention and awareness for AI was huge for those projects. It's important that "normal" people get a feeling for AIs and what they are able to accomplish.

Re: StarCraft Micromanagement with Reinforcement Learning and Curriculum Transfer

#54

Post by daemonk » Fri, Apr 20, 2018, 5:10 PM UTC

TulliusCicero wrote: post #38

daemonk wrote: post #24

Earlier quoted context omitted.

I appreciate the manual dexterity, but imagine the amount of strategy that AI assisted play would open up.

I agree with d1zzy, if you don't like the micro part of Starcraft, there are plenty of strategy games that cater to a more strategy-focused style of play.

I like the micro just as much as anyone else. But I don't agree that there is just one way to play a game and that if someone wants to deviate from it, somehow that goes against the purity of the established way. Blizzard has benefitted greatly in the past by letting the public mod their games (dota). I don't see anything wrong with extending that to Star Craft.