Daniel K Slater - Building a Pong playing AI in just 1 hour (plus 4 days training...)
3,512 views · Published 9 May 2016 · 50:18 · Indexed 31 October 2026
Channel: PyData · 2016 · Science & Technology
PyData London 2016 We will build an AI that can master the game of Pong in just 1 hour. In the course of this we will talk through some of the tools involved. Q-learning , Deep learning and Convolutional nets and how they fit into Pong. Most of the heavy lifting will be done using Google's recently released Tensorflow libraries. We will start by setting up a Python an agent in Pong that moves completely randomly. I will then talk over what Q-learning is and how it works and a bit about Convolutional nets. We will then build the actual agent using Tensorflow. Full code will be given, including links for downloading the resources required, so hopefully the audience can build this on their laptops. I would hope to give enough information that users will be able to make there own agents independently once finished. Slides available here: https://speakerdeck.com/danielslater/building-a-pong-ai GitHub: https://github.com/DanielSlater/PyDataLondon2016 00:00 Welcome! 00:10 Help us add time stamps or captions to this video! See the description for details. Want to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps
More from this channel
-
31:23
Kostas Perifanos - Authorship Attribution Using Python
-
31:08
Prash Majmudar - Measuring the Digital Economy Using Big Data
-
36:26
Ian Ozsvald - The High Performance Python Landscape
-
37:48
Mike Muller - Shared Memory Parallelism with Python
-
35:01
Martin Goodson - Most Winning A/B Test Results are Illusory
-
30:19
Mark Basham - Python for High Throughput Science
-
1:13:42
David Cournapeau & Simon Jagoe - Narrowing the Gap Between Array Computing and Databases
-
31:38
Emlyn Clay - Phython, Pharmaceuticals & Discovery