Saving the Princess with Deep Learning

on YouTube ↗18m

" summary

Shows how to train deep neural networks to play Super Mario using Python deep‑learning frameworks; covers the code, training process, and optimisations applied, and includes a live demo with code shared. Technologies mentioned include Python and multiple Deep Learning frameworks; the problem is teaching an agent to play Super Mario, approached via deep learning methods and engineering improvements.

AI-written summary · about

" chapters (8)

1. 0:00Intro
2. 2:07What is Q-Learning?
3. 3:58Q-Function
4. 5:21How to Q-Learn?
5. 6:52Deep Networks
6. 10:41Let's do this!
7. 14:25Hurdles
8. 16:13Associated Work/ Improvements

" related talks

• 56mCan I do AI?Izzet Mustafaiev · JavaDay Ukraine 2017
• 49mML: Teaching machine to learn from its own mistakes (...)Piotr Graszka · 4Developers 2020
• 01h 01mA practical guide to deep learningTess Ferrandez-Norlander · NDC Oslo 2019
• 48mMachine Takeover - Improving Your Game With Machine Learning & AIKelly Vero, Matthew Forde, Tommy Thompson, Jeff Shih · Pocket Gamer Connects Digital #2
• 37mSave the PrincessSimon Belak · EuroClojure 2017
• 01h 17mTraining intelligent game agents using deep reinforcement learningImran Rashid · PyData London 2019
• 51mDeep Learning - What is it and What It Can Do For YouDiogo Moitinho de Almeida · GOTO Copenhagen 2016
• 31mUsing Python to build an AI to play and win SNES StreetFighter IIAdam Fletcher, Jonathan Mortensen · PyCon 2018