Deep-RL: DQN — Regression or Classification?

Setup: We assume a Deep-RL example of a DQN with 4 discrete available actions, and we want to select one of the available actions depening on our estimated state

Introduction

Q-Learning

Monte-Carlo Methods

Temporal Difference

Sarsa

SarsaMax (Q-Learning)

Updating Q-Table using Sarsa

Deep Q Networks

In the Neural Network, we have: “Input=State” and “Output=Action”

Classification or Regression?

The important note here is that, each of these outputs (one for each possible action) measures the same thing! Estimated total reward!

So step back and think about it…

They all measure reward scores! So since we measure the same thing in multiple outputs, then the output with the highest reward over the same measurement is the topmost candidate.

--

--

--

MSc Computer Science. — Software engineer and programming instructor. Actively involved in Android Development and Deep Learning.

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

New Ebook: SnapML in Lens Studio—An Ultimate Guide

Twitter Sentiment Analyzer

Snapshot Ensembles: Leveraging Ensembling in Neural Networks

Learn RandomForest Classifier from classifying Mushrooms as Edible or Not-Edible!

Classifying Crisis Reports

See Reinforcement Learning from Human Learning

A Road Map for Deep Learning

NLP Guide 101: Tokenization and Methods to Perform Tokenization

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
Ioannis Anifantakis

Ioannis Anifantakis

MSc Computer Science. — Software engineer and programming instructor. Actively involved in Android Development and Deep Learning.

More from Medium

Visualization of deep neural networks

Scaling and gradient descent optimization in neural network

Seaborn Coloring for Continuous Variables

Customer Segmentation for Arvato Financial Services