Deep Learning: Game AI with Self-Play

Hello Deep Learners,

We kindly invite you to our next Deep Learning meetup on March 19, hosted by Magenta Telekom (T-Mobile Austria) in St. Marx! Our topic will be Reinforcement Learning for Game Playing.

***

Agenda

18:30

• Introduction by the VDLM organizers
• Welcome by the host

18:45

• Artificial Intelligence for the Pen-and-Paper Game "SIM"
  Paul Puntschart, cloudflight

19:45

• Announcements: Events & Job Openings

20:00

• Networking & Discussions

21:30 Wrap up & End

Talk Abstract: Artificial Intelligence for the Pen-and-Paper Game "SIM"
Paul has loved math and games since childhood. Over the last 5 years he has been using AI to teach his computer to learn and play all kind of games. He trained his computer to play TicTacToe, Jungle, Chess, and even NetHack - a dungeons and dragons single player console game. Then he stumbled upon the pen-and-paper game "SIM". SIM is so easy to explain and so easy to play that he instantly fell in love with it. He programmed it on one evening with Python and let his computer play and
learn it overnight with a simplified implementation of self-play based reinforcement learning based on the AlphaGo Zero paper (Silver et al). Join this talk to see the results, to learn how to set it up on your own and finally to play a game versus the AI yourself. If you dare.

Hot Topics & Latest News:
Do you have some interesting breaking news about Deep Learning? Did you read an interesting paper that you want to share? Did you create an exciting application or achieve some break-through? It would be great to share this in our meetup's Hot Topics section! Please get in touch through contact@vdlm.at

Please note that this meetup has a limited capacity of 100 participants (we allow more signups due to usual no-shows).

We are looking forward to seeing you!