2016.03 | Artificial intelligence | Deep learning | Atari breakout

I’ve played Atari Breakout during my childhood and I am sad now knowing that computers can beat humans in several tabletop and video games… Google’s DeepMind computer program has shown its efficiency using a combination of artificial neural networks and deep reinforcement learning to improve its own capabilities with gaming… It has recently beaten Lee Sidol, a top-ranked player of the Chinese board game Go, as has been recently broadcasted in TV, newspapers, etc… this reminded me a video I saw last year showing how DeepMind program was learning video-games, improving itself up to a super-superhuman level and I wanted to share this with you (see video below).

There always exists the most efficient “solution” to a given video/tabletop games?

Artificial intelligence 1 – Humans 0….. what’s next?  😀

 

 

 

 

 

Published by

Antonio Abellan

Hello!, My name is Antonio Abellan, I am a research and teaching assistant at the Risk Analysis group, Institute of Earth Sciences, University of Lausanne (Switzerland). My research focuses upon the 3D study of different natural hazards in Alpine, Permafrost and Polar environments.... you can take a look at my profile here: http://3d-landslide.com/about-me/

Leave a Reply

Your email address will not be published. Required fields are marked *