While StarCraft is just a game, albeit a complex one, we think that the techniques behind AlphaStar could be useful in solving other problems. For example, its neural network architecture is capable of modelling very long sequences of likely actions - with games often lasting up to an hour with tens of thousands of moves - based on imperfect information. Each frame of StarCraft is used as one step of input, with the neural network predicting the expected sequence of actions for the rest of the game after every frame. The fundamental problem of making complex predictions over very long sequences of data appears in many real world challenges, such as weather prediction, climate modelling, language understanding and more. We’re very excited about the potential to make significant advances in these domains using learnings and developments from the AlphaStar project.


We also think some of our training methods may prove useful in the study of safe and robust AI. One of the great challenges in AI is the number of ways in which systems could go wrong, and StarCraft pros have previously found it easy to beat AI systems by finding inventive ways to provoke these mistakes. AlphaStar’s innovative league-based training process finds the approaches that are most reliable and least likely to go wrong. We’re excited by the potential for this kind of approach to help improve the safety and robustness of AI systems in general, particularly in safety-critical domains like energy, where it’s essential to address complex edge cases.


Achieving the highest levels of StarCraft play represents a major breakthrough in one of the most complex video games ever created. We believe that these advances, alongside other recent progress in projects such as AlphaZero and AlphaFold, represent a step forward in our mission to create intelligent systems that will one day help us unlock novel solutions to some of the world’s most important and fundamental scientific problems.


https://deepmind.com/blog/alphastar-mastering-real-time-strategy-game-starcraft-ii/ 에서 발췌함



대체 왜 APM을 제한하냐 마냐가 논란이 되는건지 모르겠음

알파스타의 학습 과정을 보면 APM 제한이 있든 없든 말도 안되는 마이크로컨트롤은 나올 일이 없잖음

그걸 제쳐두고라도 딥마인드는 위에 밑줄친것처럼 알파스타가 각 프레임을 인풋으로 받아서 나머지 게임의 일련의 프레임을 예상하는 과정을 알파스타 프로젝트에서 얻었고 그걸 다른 문제에 적용하는 게 목표지 다른 게 아니잖음.

인간이랑 똑같은 컨트롤으로 이김 → 다른 문제에 적용 가능

인간보다 빠른 컨트롤으로 이김 → 다른 문제에 적용 불가능 ???


말도 안되는 마이크로 컨트롤으로 이기는거면 예상이 무의미해지는거니까 의미없는게 맞지만 인간이 쓰는 컨트롤을 하지만 그 컨트롤이 더 정교하고 더 빠른게 문제가 되냐는 회의적임 ㅇㅇ