Deep Reinforcement Learning to Play StarCraft
1–10 of 51 posts
Re: Deep Reinforcement Learning to Play StarCraft
#2Screw Go. Beating the Terran Emperor in a game of Starcraft is when the computers will finally take over the world.
It would be interesting though. How would a program that has PERFECT micro fare against a professional Starcraft player. Would a program reliably figure out how to kill 10 banelings with a few marines and a medivac by using the fact you can micro them to be able to do it without taking losses? Even if it could, would it know WHEN its even worth it to do so?
Re: Deep Reinforcement Learning to Play StarCraft
#3Screw Go. Beating the Terran Emperor in a game of Starcraft is when the computers will finally take over the world. It would be interesting though. How would a program that has PERFECT micro fare against a professional Starcraft player. Would a program reliably figure out how to kill 10 banelings with a few marines and a medivac by using the fact you can micro them to be able to do it without taking losses? Even if i…
They must constrain the AI to effectively only "click" on things at a rate and as far apart from the last thing clicked on such that a human could do it with a mouse
Re: Deep Reinforcement Learning to Play StarCraft
#4After loosing on the Go territory seams like fb is trying to challenge Alphabet on StarCraft. DeepMind already declared they will go for StartCraft as a next challenge does it mean that they accept the challenge? I'm actually happy to see what could be the result! The only weak point for the StarCraft community is that it would be on SC1 and not SC2.
Re: Deep Reinforcement Learning to Play StarCraft
#5Screw Go. Beating the Terran Emperor in a game of Starcraft is when the computers will finally take over the world. It would be interesting though. How would a program that has PERFECT micro fare against a professional Starcraft player. Would a program reliably figure out how to kill 10 banelings with a few marines and a medivac by using the fact you can micro them to be able to do it without taking losses? Even if i…
In the past, Q-learning has led to models that perform at a superhuman level, so I wouldn't be surprised to see something similar.
Re: Deep Reinforcement Learning to Play StarCraft
#6After loosing on the Go territory seams like fb is trying to challenge Alphabet on StarCraft. DeepMind already declared they will go for StartCraft as a next challenge does it mean that they accept the challenge? I'm actually happy to see what could be the result! The only weak point for the StarCraft community is that it would be on SC1 and not SC2.
Gabriel Synnaeve was already working on this long before joining FB.
Re: Deep Reinforcement Learning to Play StarCraft
#7Screw Go. Beating the Terran Emperor in a game of Starcraft is when the computers will finally take over the world. It would be interesting though. How would a program that has PERFECT micro fare against a professional Starcraft player. Would a program reliably figure out how to kill 10 banelings with a few marines and a medivac by using the fact you can micro them to be able to do it without taking losses? Even if i…
There are already incredibly good micro StarCraft AI, able to operate at thousands of APM - this isn't the limiting aspect of current StarCraft AI.
The "Hard" part of StarCraft is that it is a huge Rock Paper Scissors game with only the information you fight for. You have to be able to piece together a picture of your opponents actions and forces from small cues.
Re: Deep Reinforcement Learning to Play StarCraft
#8I think Starcraft is a very interesting challenge for AI because it involves planning in an environment that is only partially observable: you must scout in order to see what your opponent is up to, and even then, you don't see everything. If DeepMind works on this, I really hope that they constrain the AI (APM-wise) so that its only chance of winning is by good planning and strategy, not super-fast micro.
Re: Deep Reinforcement Learning to Play StarCraft
#9Screw Go. Beating the Terran Emperor in a game of Starcraft is when the computers will finally take over the world. It would be interesting though. How would a program that has PERFECT micro fare against a professional Starcraft player. Would a program reliably figure out how to kill 10 banelings with a few marines and a medivac by using the fact you can micro them to be able to do it without taking losses? Even if i…
There are already incredibly good micro StarCraft AI, able to operate at thousands of APM - this isn't the limiting aspect of current StarCraft AI. The "Hard" part of StarCraft is that it is a huge Rock Paper Scissors game with only the information you fight for. You have to be able to piece together a picture of your opponents actions and forces from small cues.
Wow, I hadn't seen this before.
Here is "Automaton 2000" controlling 20 marines vs 40 banelings, without losing a single unit.
https://youtu.be/DXUOWXidcY0?t=52
Pretty cool.
Re: Deep Reinforcement Learning to Play StarCraft
#10After loosing on the Go territory seams like fb is trying to challenge Alphabet on StarCraft. DeepMind already declared they will go for StartCraft as a next challenge does it mean that they accept the challenge? I'm actually happy to see what could be the result! The only weak point for the StarCraft community is that it would be on SC1 and not SC2.
Actually SC1 is the defacto choice when talking about StarCraft esports and the best choice since the best SC players have been honing their skills on SC1 for a long time (see South Korea SC1 esports scene).