The alpha go documentary was pretty good, this would make a nice sequel

I was gratified to see how gracious the players were in the face of such a defeat.

We need a game called Alpha so that DeepMind can create AlphaAlpha in a truly alphaic way.

Being able to se the whole map at once is an incredibly massive advantage.

Please make this a full docu as well. Alphago was one of the best docus of the past years.

For the sake of us, i only hope that your ia safety team is the strongest of all.

Congrats DeepMind. You're an impressive team.

Came here after the AlphaGo Full Documentary. Impressive stuff!

I like how Alphastar worked around APM limitation basically by saving up his available APMs for when they are needed most and then use them in bursts :)

Alphastar vs OpenAI

I can't wait to see the progression! Sooner or later it should be able to play any race, against any race. It would be interesting to see if it prefers playing a certain race, or if it perhaps chooses dependent on certain maps or opponents etc

Brilliant, brilliant, brilliant, Deep Mind has done it again! Well done, very impressive!

This work inspires me to get into computer science.

I love this videos, keep updating us of the backstage

Great work. I think this will have applications in power system optimization.

Keep up the good work! You have no idea the smile you bring to the faces of those who love to see technology advance! Thank you for all the hard work! Love it!

Congratulation on that achievement DeepMind team. Can't wait to read more about your model when you'll release a paper later. I wonder if you developped a macro strategy policy that gives short-term objectives to a micro policy ? or if you have only one policy network coupled to a LSTM for memory ?

Vote up if you want to watch AlphaStar vs Serral

I am glad our AI overlords are learning so quickly to defeat our puny human armies. I also hope they learn to read youtube comments so they know how much us loyal subjects love them. bº*r#i+n$g h)e]l&p sorry for that, must have pressed my elbow against the keyboard.

Oh my god, this video gave me the shivers. Awesome

I know it had superhuman micro, but let's talk about how amazing it is that it plays human strategies so well, and plays like a human.

Major Fan of AlphaStar overcoming programming complexities for a better future.

absolutely incredible work. would love to see this taken to a team-based game like dota 2, and see if a machine learning bot can climb to the highest rank in the solo queue of that game too. presents a new challenge with the addition of having to cooperate with unpredictable and unreliable human teammates to achieve victory, in five different possible roles with hundreds of heroes and millions of unique team configurations and items and so on.

Now it is the time to see the clash of A.I : OpenAI Five VS DeepMind AlphaStar .

maybe worth mentioning: Mana beat AlphaStar on the live stream match afterwards

The thing about AI that people underestimate is that the volume of automated training can quickly help an AI to overcome the mistakes in its learning. With humans, it's very hard to convince someone they're wrong, let alone change someone's mind, and often you just have to breed new humans and hope the old ones die off fast enough so that their mistakes don't get meaningfully passed on to the next generation.

Amazing and scary at the same time...

Imagine a grand tournament held each year where the best players in each e-sport try to beat such an AI. I'm sure that would sell some tickets.

It's amazing how calm these pros are when they lose. I get flustered and upset and if I lost 5-0 I'd feel humiliated. They let it slide off like water to a duck's back.

They are coming!

Model human decision making. Model an army. Model a map. Use enough time and computing power. The military is already knocking.

To many nerds together.I am afraid of what they can create next. Keep doin a good job

The alpha go movie was one of the best documentaries I have seen.

It can see the whole map? That has to be the most important and difficult Challenge to over come IMO.

I love Reinforcement Learning and its variants, hopefully would be working with you guys or somewhere else if not, creating agents that surpass humans by far! 😊

They're going to be everywhere!

Interesting video. Reminds me of the old early days of AI back in the early 80s with LISP machines.

A remarkable feat no doubt, but it would have been great to see AlphaGo face the top 5 in the world including Serral with their own mice and keyboards etc. It makes a big difference.

Fascinating!

The two big things are APM spikes that look normal but are completely impossible because of the precision and camera.

Very interesting, I hope you can perfect SC2

I would love to see some games AI vs AI, just to see what happens

This is Amazing! Whats next?

Are you planning to do the same for Warcraft 3? There is defo a need for fresh strategies in the game so it might be a no brainer :) Great job!

You guys have the best job ever...

Fascinating!! Looking forward to where this type of AI leads us.

I'm not yet completely satisfied in Alphastar. 1) The APM cap has to be changed. Alphastar had lower mean APM than the human pros but in engagements its APM shot up to 1500's. That equals 25 actions in a second. No human player is capable of doing this with great precision. The APM should be capped in two ways. Firstly, the mean averge per minute as they did in this demonstration but more importantly, Alphastar should be restricted in such a way that the huge spikes are not possible. Perhaps a limit on how many actions it is allowed to do within a second? 2) Especially in the games against Mana, Alphastar demonstrated inhumane ability to control its units. It won game 4 because of how clean its micro was, not because it outplayed Mana. Good army control is impressive and clearly requires a certain level of intelligence but this kind of perfect blink stalker micro doesn't really exist within the game. Deepmind should differentiate between the agents intent and execution. Perfect micro is more than just speed. Precision is much more important. Human pros missclick all the time. There needs to be a random element in how Alphastar controls its units. 3) The agents seemed to be stuck on the strategies that they had trained in. I'm not entirely sure if this is the case but I think there was zero tech switches from Alphastar. It seemed to be stuck on the army compositions it initially chose. In a few games the composition was clearly sub-optimal considering what the human player had. Reacting to the scouted information and actually being able to flexibly adjust strategy on-the-fly is exactly the kind of intelligence that Deepmind should strive towards. While Alphastar is impressive and Deepmind limited its mechanical ability a little it was still very clear to someone familiar with Starcraft that it won mostly because of its superhuman mechanical ability. It could perceive all of its own units at the same time, it had superhuman mouse precision and macro abilities. TL;DR Cool but not quite there yet. Alphastar won because of superhuman mechanical abilities. I want to see a bot that plays as slow and as sloppy as the average pro player and still be able to achieve >50% winrate against the best in the World.

the best training coach for the pros out there in my honest opinion. Give them few weeks of fighting the A.i and let them loose against humans after; i predict a win for those who trained and fought with A.i

Impressive deep mind team, this is very cool and exciting! I think the improvement between TLO games and Mana games were improving the mechanics to beyond-human levels. Do you plan to scale back the "effective APM" to more human levels now that it is hitting like 1200-1500 apm (mostly effective, I assume?) in one reply I watched.

Alphastar definitely plays to his strengths. Which are micro and multitasking.

This is like watching the scientists in Jurassic Park hold a baby T-Rex and not realizing that one day it’s going to grow up and eat them.

They shouldn’t allow the computer to see more than what a player can. Make the computers only input the output of the screen.

If only TotalBiscuit is still alive today to cast this match.

I think it's extremely cool what you're doing but I'd be interested in knowing exactly what reaction time you used for AlphaStar and also I think you said it was performing at 500APM, I think it would be interesting to see how it changes and adapt when you turn down the APM. How does it behaves at 450? 400? 300? I think there are a lot of extremely cool observation that can be done by looking at AlphaStar and especially kind of see where the victories come from, of course it will be a mix of strategy and mechanics, I'm curious to see what heppens when gruadually limiting more and more the "mechanical" skills (APM) of the machine. Anyway really solid work, keep it up!

Getting gouse bumps of excitement watching this

so fascinating

DeepMind had to consider Korean players with Starcraft 1 (remastered).

I've been running Fold@Home on my PC for years, and AlphaFold has leapfrogged over any previous efforts by a wide margin. As with any technology, the applications have good and bad prospects. Let's hope the good outweighs the bad in future.

Where can we see the replays?

Wow!😃 I got a really big simple during the match and when AlphaStar won the matches

Well, you forgot that Mana won against the Agent who was not allowed to be everywhere on the map at the same time, although more to it glitching out than that. Still, good work. Lets see where this will go.

Are you able to differentiate any equation🔔 upto infinity???

I can see overfitting problem of undetermined (hidden) situation on every replay game. How can solve this.

when is the serral vs alphastar match?

I'd like to see the AI try to play a team of pros at the same time

Nice to see humans that outsmarted other spicies with their tools are now been outsmarted by that tools.

This Documentary is gonna be BIG! (Am I the only one hyped?)

Working at DeepMind would be a dream come true, but sadly they are based in London and i live in the US.

Good job you'll do great for the world

1:40 “Alcohol is not just to defeat these players. Alcohol is to do it in the right way.” Wait, there was drinking involved?

Waiting for the day DeepMind develops an AI for Dota 2. I wanna see OpenAI 5 vs AlphaDota

What game would be next level up for ai?

Can this AI be used for developers to balance their game before relase and for future expansions, or would the players and AI ability be so different, that the balance for the AI would in the end lead to unfair plays players would use?

The only issue is yes the actions per minute are human like but it if go to effective actions per min during engagements the alphastar reached numbers of 600-800 per minute while mana was at about 400. Effective actions per minute ate the ones that matter.

David Silver is an inspiration to many 🙌

It will be interesting to impose human-like limitations on an AI, like clicks per second limitation, innate imprecision, etc. We could find out if the AI 'brain' was beating the human brain or if it was winning based on speed, precision, multi tasking, etc. But we won't impose those restrictions on AIs we employ to address real world problems, so I am also interested in how unrestricted AI does against the best humans.

What's the background music?

They should have picked Zerg as a main race. Fits better thematically I feel. DeepMind being the Overmind. The hive itself.

Guys I watched the live stream and on the oversaturation on probes, maybe the tought process of the agent was that the enemy will attack me with a few units> I loose X numbers of probes> hence I make more probes. We saw that the agent was at 24 probes when TLO attacked with 2 adepts and after the attack the agent had 17 probes in main and another 3-4 going for the expansion...

When we can see Zerg?

what programming language did they used ?

Alphastar appears to have won because of its superhuman mechanical ability to see and control its units at all times rather than a superhuman mind. Mouse movement speed, visible units on-screen, Actions per SECOND, precision, reaction time - all of these mechanical abilities need to be taken into consideration much more seriously/restrictively if we want to develop a Deep MIND rather than a technique impossible for humans to execute. For me, the excitement around AI is the intelligence, not the aimbot. Lovely project and clearly a lot of excellent work so far but personally it looked very unfair to the pros.

Even if you can make the same amount of clicks, you're still have an advantage by being able to think 1000 times faster. It's not the amount of clicks that matters in Starcraft, it's how valuable and precise they are.

I can't wait for it to be tasked with material science innovation. i.e. "We need a material that has 1000x the tensile strength of steel, but flexible like fabric...."

Imagine if they Dev a tilt focused build for alpha star or whatever variant they make for dota 2 or lol or maybe even csgo valorant etc

Loved it!! Deepmind... YOU ROCK!!! :))

I wanna see the documentary like alphago bout alphastar

Did they set up reaction time, map visibility and clicks per minute as human?

I want to see Serral vs AlphaStar

Awesome

The AI can see the whole map? That’s quite a huge advantage for a game in Starcraft. Even if u limit the APM that doesn’t really make a huge difference.

After watching the games, I think the limitation should be imposed on EPM not APM. As a fan who has watched starcraft games since 2009, I would say no one ever could do the micro-control like AlphaStar did to Phenix and Stalkers. For a human player, select more than three target units instantly is very tricky. When human players tried to do control like this, they might be failing to select any unit, where the action is counted into "APM" not "EPM". Numerous useless actions always happen during a game for human players. My conclusion is DeepMind considers the fairness in terms of APM's quantity, but they should have introduced another aspect which is the quality of "APM". The solution is simple, either switching to EPM or gives a probability (close to human players) of mis-operation.

I'd love to watch Deep Mind Play Skyrim...

What will be the next DeepMind's move?

But can it defend a cannon rush in 2v2 with a teammate unwilling to do anything but get BCs?

Come to Korea. Revenge match in Starcraft for Lee Sedol!!!

They need to make AlphaMayweather.

I like how even the people that developed the AI had no idea what the hell it was doing, and expected it to lose.

In the future games are won by Ai fighting each other which could be a good thing to watch

I think that they should try to make Alphastar win against human while using as low APM as possible, in my opinion I would be awesomely cool if they set that as the goal condition for Alphastar. Imagine to see it beat a human while its mean APM are at 60.