Google DeepMind使用深度强化学习创建了一个人工智能程序,该程序可以玩Atari游戏并将自身提升到超人的水平。它能够玩许多Atari游戏,并结合了深度人工神经网络和强化学习功能。在用算法展示出最初的结果之后,Google几乎立即以数亿美元的价格收购了该公司,因此得名Google DeepMind。请欣赏影片,如果您对深度学习有任何疑问,请告诉我!
______________________
为你推荐:
1. DeepMind的AlphaGo如何击败Lee Sedol-https://www.youtube.com/watch?v=a-ovvd_ZrmA&index=58&list=PLujxSBD-JXgnqDD1n-V30pKtp6Q886x7e
2. DeepMind如何克服深度学习(AlphaGo)-https://www.youtube.com/watch?v=IFmj5M5Q5jg&index=42&list=PLujxSBD-JXgnqDD1n-V30pKtp6Q886x7e
3. Google DeepMind的深度Q学习和超人Atari游戏玩法-
如果您想查看更多类似的内容,请订阅:http://www.youtube.com/subscription_center?add_user=keeroyz
-原始的DeepMind代码:https://sites.google.com/a/deepmind.com/dqn/
-Ilya Kuzovkin的叉子,带有可视化效果:
https://github.com/kuz/DeepMind-Atari-Deep-Q-Learner
-此补丁修复了重新加载预训练网络时的可视化问题。在第一个评估批处理完成后(通常是几分钟),将出现该窗口:
http://cg.tuwien.ac.at/~zsolnai/wp/wp-content/uploads/2015/03/train_agent.patch
-此配置文件将使用少于1GB的VRAM运行Ilya Kuzovkin的版本:
http://cg.tuwien.ac.at/~zsolnai/wp/wp-content/uploads/2015/03/run_gpu
-有关此深度学习技术的原始《自然》论文可在此处获得:
http://www.nature.com/nature/journal/v518/n7540/full/nature14236.html
-还有一些不在收费区后面的镜子:
http://www.cs.swarthmore.edu/~meeden/cs63/s15/nature15b.pdf
http://diyhpl.us/~nmz787/pdf/Human-level_control_through_deep_reinforcement_learning.pdf
网址→https://cg.tuwien.ac.at/~zsolnai/
Twitter→https://twitter.com/karoly_zsolnai。
Do you think that within the decade q-learning could manage to figure out how to play super Mario brothers on the nes with only visual input. It would have to learn the concept of lives and fail states, some things could play naturally like if it got to the first castle it knows that it needs to move to the right to progress, and certain actions can give you score. It would get to bowser, the sprite is moving. So it might be an enemy, or it could be a platform. But you die when you touch it, so it determines that this is a hazard that is mobile. It figured out that stationary hazards like reaching the bottom of the screen it can't kill with fireballs, but a mobile hazard can, up to this point. So it shoots it with fireballs, maybe dying once or twice to the fire before realizing that you cant jump on that. So it either avoids the enemy by jumping over it or going around it, or blasting it with fireballs. Once the enemy is clear, it will continue to navigate to the right, and it sees the score going up from the extra time. Probably way harder to do than that but it could be feasible to do. Something like Zelda? maybe later.
it is very interesting
I’m sure this is obvious but how do you program an AI to have an open goal like “as many points as possible”?
Does it just note everything that happened in achieving a higher score and attempt to replicate that with minor changes to leave open the possibility of a better one?
Does it figure out how the game actually works (such as needing to bounce the thing back) and avoid missing it, or is this a brute force approach where it reaches that end through trial and error?
I find these things to be so interesting but very confusing lol
D.A.R.Y.L playing Atari games
The moment it finds the narrow gate.
One important point with this is that when researchers moved the "paddle" up a pixel the AI couldn't play the game at all even though it was at superhuman master level. So it was not able to abstract to something that was basically the exact same. This is an example of a hypersmart computer that lacks the common sense of a mouse.
How did you get DeepMind program?
I remember as a kid my brothers and I were struggling over the same level on a video game. We had all taken a shot at it for an entire day and frustrated, we went to bed. We woke up the next morning and immediately powered on the playstation and took our controllers. Just as we were ready to sit on the couch and move our controls, we suddenly realized that the player was moving without our controlling it. Confused, we looked at one another. I said, "I'm not controlling it, are you?" All of us agreed that none of us were in control. Our confusion slowly turned to awe as we watched the level completed with an exactness and expertise never seen before. Our awe quickly turned to glee and we began shortly triumphantly at the screen "Go computer! Kick their butts!" And cheering on the A.I. haha. It won the level and will forever stay in our minds as a glorious day, when the computer decided to look fondly upon us and give us kids a second chance 🙂
If AI can accomplish all intellectual tasks, the only field left to us human being is to develop spiritual values and moral virtues: courage, wisdom, justice, temperance
from life 3.0
Wow. That impressive. Now get it to make paperclips!
GOO GULL=EVIL!!!!
GOO=SIHT!!!
EVIL=GOOGLE!!!
Liked
Who else is here from Max Tegmark's book "Life 3.0"?
사람은 기계를 이길 수 있을까…
이길 수 없다면 이 이상의 발전은 그만둬야 하는게 아닐까
we're all doomed motherfuckers
If you try to teach it Qix you better also teach it to kick the machine in frustration.
Yes the tunnel was an obvious technique.
the thing is though, does it really "see" that it has tunneled through and bounced the ball off the back, or did the network simply NOT select against that behavior of tunneling? To test its understanding of delayed gratification, you'd have to introduce a consequence for tunneling that the AI "sees" is worth taking.
Brick by Brick….. piece by piece….Tomato….Tamato what's the difference WatchTower/Deep Mind…?
This is what is going to kill all of us.
Let it solve the hacking problem of GTA V! Really need it!
What would REALLY be astonishing is that if learning algorithms can learn to play games like Mario, which is an NP problem, they could learn to solve NP problems and tell us how. Thus leading to a unifying or differentiation between P and NP problems in general. Amazing!
Deep Thought, what is the answer to the ultimate question of life, the universe, and everything?
as long as everyone knows, this has absolutely nothing to do with the idiots at google.
It is not technically an algorithm, its an artificial intelligence that uses Q-learning with a neural network.
Max Tegmark’s book “Life 3.0” brought me here ?
It should start playing skyrim
what kind of hardware do you need to train it in 240 minutes?
We're fucked
I wonder how does it converge on a move-efficient scheme if the loss only covers maximizing the score? Would a 'catch-all' scheme be more risky?
Very interesting stuff indeed! We are living in exciting times!
Find a game disc is supposed to be is it supposed to be a ball game or soccer
you can make similar program with DQN and keras-rl: https://noteoneverything.blogspot.com/2018/02/reinforcement-learning-of-atari-breakout.html
Interesting, but one thing I wonder is why DeepMind tried to play in effective way that it dug the hole rather than just receiving every drop of the ball which it could have done as well.
When it learns to play dungeons and dragons we are all doomed…
So, what about a next level AI created by a next level AI by a superhuman AI…. Maybe 'they' can figure out faster than light travel.
''It realizes that digging a tunnel … is the most effective way…" Sorry, but in Breakout, you can either miss the ball or reflect the ball, but not control its direction. Disappointing that the Deepmind gurus try selling a chance event as an example of the deep insights reached by their learning algorithms. These were early days, I guess.
Amazing !
Mantis Shrimp
How many people will use ai to cheat on games…
Let him play in the "Detroit: becoming a man" ))
Keşke biri Türkçe yorum yapsa bende anlayabilsem ?
알파고님 충성충성충성
전 기계제국의 충실한 노예입니다. 핥짝핥짝