Learning to Play Games through Reinforcement Learning

Continuing with deep learning topics we have one of our first members (https://www.meetup.com/nyhackr/events/12089093/) and repeat (https://www.meetup.com/nyhackr/events/60839932/) speaker (https://www.meetup.com/nyhackr/events/205980522/), Shane Conway talking about beating video games with machine learning.

Thank you to eBay NYC (http://www.ebaynyc.com/) for hosting.

This meetup was timed to coincide with all the activity around Strata (http://www.oreilly.com/pub/cpc/108405). O'Reilly has been a long-time sponsor of this group so it is nice to have our events happening at the same time. As always, members of the group receive a 20% discount to Strata (http://www.oreilly.com/pub/cpc/108405) with code UGNYHACKR20 (http://www.oreilly.com/pub/cpc/108405).

About the Talk:

Games have long served as a challenge for AI researchers. With the recent success of DeepMind (https://deepmind.com/), there has been a major advance in the ecosystem for researching reinforcement learning problems. I will walk through OpenAI (https://openai.com/) benchmarks in Python, and demonstrate several approaches to beating Atari games including DQN, A3C, and NEC.

About Shane:

Shane Conway is a researcher at Kepos Capital, a quantitative Global Macro firm located in New York City. His research interests have centered on optimal trading problems. He has a degree in Electrical Engineering from Columbia University. He can be reached through twitter @statalgo (https://twitter.com/statalgo).

Pizza (https://nyhackr.org/pizzapoll.html) begins at 6:30, the talk starts at 7, then after we head to the local bar.