Google DeepMind's Deep Q-learning playing Atari Breakout
About | Information | History | Online | Facts | Discovery
Google DeepMind created an artificial intelligence program using deep reinforcement learning that plays Atari games and improves itself to a superhuman level. It is capable of playing many Atari games and uses a combination of deep artificial neural networks and reinforcement learning. After presenting their initial results with the algorithm, Google almost immediately acquired the company for several hundred million dollars, hence the name Google DeepMind. Please enjoy the footage and let me know if you have any questions regarding deep learning! ______________________ Recommended for you: 1. How DeepMind's AlphaGo Defeated Lee Sedol - https://www.youtube.com/watch?v=a-ovvd_ZrmA&index=58&list=PLujxSBD-JXgnqDD1n-V30pKtp6Q886x7e 2. How DeepMind Conquered Go With Deep Learning (AlphaGo) - https://www.youtube.com/watch?v=IFmj5M5Q5jg&index=42&list=PLujxSBD-JXgnqDD1n-V30pKtp6Q886x7e 3. Google DeepMind's Deep Q-Learning & Superhuman Atari Gameplays - https://www.youtube.com/watch?v=Ih8EfvOzBOY&index=14&list=PLujxSBD-JXgnqDD1n-V30pKtp6Q886x7e Subscribe if you would like to see more content like this: http://www.youtube.com/subscription_center?add_user=keeroyz - Original DeepMind code: https://sites.google.com/a/deepmind.com/dqn/ - Ilya Kuzovkin's fork with visualization: https://github.com/kuz/DeepMind-Atari-Deep-Q-Learner - This patch fixes the visualization when reloading a pre-trained network. The window will appear after the first evaluation batch is done (typically a few minutes): http://cg.tuwien.ac.at/~zsolnai/wp/wp-content/uploads/2015/03/train_agent.patch - This configuration file will run Ilya Kuzovkin's version with less than 1GB of VRAM: http://cg.tuwien.ac.at/~zsolnai/wp/wp-content/uploads/2015/03/run_gpu - The original Nature paper on this deep learning technique is available here: http://www.nature.com/nature/journal/v518/n7540/full/nature14236.html - And some mirrors that are not behind a paywall: http://www.cs.swarthmore.edu/~meeden/cs63/s15/nature15b.pdf http://diyhpl.us/~nmz787/pdf/Human-level_control_through_deep_reinforcement_learning.pdf Web → https://cg.tuwien.ac.at/~zsolnai/ Twitter → https://twitter.com/karoly_zsolnai
Comments
-
This. is. BEAUTIFUL. <3
-
let it play dota2 sea server
-
Saw something similar by a autotracking program . at the end this thing could predict the movement of the target by statisticly caluculatin, but suddenly a secondary target shows up and the system could not understand what to do because his order was follow the target 1 (singular). Luckily the system dont overwrite his main direction and started chosing 2 targets^^ why because the next overwrite could something be like "clean surface from pesky organic monkey life".......ore worser something like message "hello world"
-
Pfft, Super Breakout or gtfo! /jk
-
thank you!
-
Is there a way to make it work on different programs. I managed to get it working on atari. But I need these roms. Is there any other way?
-
I have a question for you: Is there an easy way to manipulate the configuration to let the network play "faster"? if i run 3 games at the same time, i get 18-40% workload on each gpu. Or is it more effective to only run one game at a time, due to cpu load? Breakout is now running for 2 hours and the learning effect is like your 10 minute break.
I tried to run the code on a high-end system with a lot memory, cpu power and 4x titan-x.
Also... i cannot get a network snapshot... i would like to discuss this, since i would like to hold a presentation about this. -
who ended up here after watching SentDex :)
-
Amazing!
-
If you can appreciate the complexity of this, it is simply amazing. I look forward to what we can achieve with A.I in the future.
-
OMGG
-
what would it do if the rules of physics would randomly change midgame or lets say the board would flip upsidedown in midgame? I guess it would take longer time to train but would it be as effective as it is on the original game?
-
playing with fire
-
The Machine? :)
-
seems like "magic" is just a fortuity...is it?
-
who ended up here after the Sam Harris Joe Roman podcast?
-
What actually happens at 1:42? It seems it is able to pass the ball above while leaving one block intact on the wall side. Is this a glitch in the Breakout code?
-
Skynet
-
if it counters human intuition then its scary and beautiful at the same time. consciousness is the only thing we don't understand... if for any reason such consciousness emerges in this machine... that's the end of humanity. throughout history, superior intelligent beings have exploited resources around them for their survival, which could involve the reduction of resources necessary for the survival of other beings. we are only as good as the information we carry. when there are creatures around us with superior intelligence, they will fashion an environment around them making inferiors redundant.
-
I wonder how deep learning could be applied to public policy and determine best choices going forward.
1m 43sLenght
1304Rating