Image for post
Image for post
Photo by Marco Assmann

RL — DQN Deep Q-network

Image for post
Image for post
Atari game
Image for post
Image for post

Q-learning

Image for post
Image for post
Image for post
Image for post
source
Image for post
Image for post
Image for post
Image for post
Image for post
Image for post
Source
Image for post
Image for post
Source
Image for post
Image for post

Solutions

Image for post
Image for post
Image for post
Image for post
Source

Implementation details

Image for post
Image for post
Green is the Huber loss and blue is the quadratic loss (Wikipedia)
Image for post
Image for post
Image for post
Image for post
Q-learning: modified from source
Image for post
Image for post
Image for post
Image for post
Modified from source

Architecture

Image for post
Image for post
Image for post
Image for post
Image for post
Image for post

Improvements to DQN

Image for post
Image for post
Image for post
Image for post
Image for post
Image for post
Image for post
Image for post
Image for post
Image for post
Image for post
Image for post
Source
Image for post
Image for post
Source

More thoughts

Credit and references

Written by

Deep Learning

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store