Skip to content

reinforcement learning course at Data Science Retreat

Notifications You must be signed in to change notification settings

RabbitJackTrade/dsr_rl

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

A glance at reinforcement learning

Materials for the reinforcement learning course at Data Science Retreat. This course is aimed at people with a grasp of supervised learning but no understanding of reinforcement learning.

The course materials are

This project is built and maintained by Adam Green - adam.green@adgefficiency.com.

This repo contains useful machine learning and reinforcement learning literature.

to start with for reinforcement learning

Sutton & Barto - Reinforcement Learning: An Introduction - 2nd Edition (in progress)

RL Course by David Silver - slides - lecture videos

Li (2017) Deep Reinforcement Learning: An Overview

to start with for machine learning

For neural networks - Deep Learning - Ian Goodfellow, Yoshua Bengio and Aaron Courville

For everything else (linear models, random forests etc) - Elements of Staistical Learning - Trevor Hastie, Robert Tibshirani and Jerome Friedman

videos & lectures

The Long-term of AI & Temporal-Difference Learning (Richard Sutton - DeepMind)

Deep Reinforcement Learning (John Schulman - OpenAI) - policy gradients

Deep Reinforcement Learning and Real World Challenges (Raia Hadsell - DeepMind)

Deep Reinforcement Learning in TensorFlow (Danijar Hafner - Stanford)

2017 NIPS David Silver Keynote - AlphaZero

blog posts

Deep Reinforcement Learning: Pong from Pixels

Deep Deterministic Policy Gradients in TensorFlow

AlphaGo, in context

World Models

cool open source RL projects

gym - Open AI

baselines - Open AI

rllab - Berkley

About

reinforcement learning course at Data Science Retreat

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 54.3%
  • Jupyter Notebook 43.0%
  • Shell 1.4%
  • CSS 1.3%