IqraShahzad1/RL_refs

RL references

Books

• Reinforcement Learning: An Introduction (Second Edition, in progress)

  • Richard S. Sutton and Andrew G. Barto
  • https://github.com/ShangtongZhang/reinforcement-learning-an-introduction

• Reinforcement Learning: An Introduction

  • ebook
    • http://incompleteideas.net/sutton/book/ebook/

• Algorithms for Reinforcement Learning

  • Csaba Szepesvári

Lectures

• UCL Course on RL

  • David Silver
  • 2015
  • University College London
  • Lecture Videos (YouTube)
    • https://www.youtube.com/watch?v=2pWv7GOvuf0

• MIT 6.S094: Deep Learning for Self-Driving Cars

  • 2017
  • MIT
  • Lecture Videos (YouTube)
    • https://www.youtube.com/playlist?list=PLrAXtmErZgOeiKm4sgNOknGvNjby9efdf

• CS 294: Deep Reinforcement Learning, Fall 2017

  • Sergey Levine
  • 2017
  • UC Berkeley
  • Lecture Videos (YouTube)
    • https://www.youtube.com/playlist?list=PLkFD6_40KJIznC9CDbVTjAF2oyt8_VAe3

• CS 294: Deep Reinforcement Learning, Spring 2017

  • Sergey Levine, John Schulman, Chelsea Finn
  • 2017
  • UC Berkeley
  • Lecture Videos (YouTube)
    • https://www.youtube.com/playlist?list=PLkFD6_40KJIwTmSbCv9OVJB3YaO4sFwkX

• CS 294: Deep Reinforcement Learning, Fall 2015

  • John Schulman, Pieter Abbeel
  • 2015
  • UC Berkeley

• CS 287: Advanced Robotics, Fall 2015

  • Pieter Abbeel
  • 2015
  • University of California at Berkeley

• Deep Reinforcement Learning and Control Spring 2017, CMU 10703

  • Katerina Fragkiadaki, Ruslan Satakhutdinov
  • 2017
  • CMU

• REINFORCEMENT LEARNING 2016/2017

  • 2016
  • The University of Edinburgh

• CS7032: Agents, AI & Games

  • Saturnino Luz
  • Trinity College Dublin

Videos

• Deep Learning (DLSS) and Reinforcement Learning (RLSS) Summer School, Montreal 2017

• Deep Reinforcement Learning Through Policy Optimization

  • Pieter Abbeel
  • Jan 23, 2017

• Deterministic Policy Gradient Algorithms

  • David Silver
  • DDPG

• Deep Reinforcement Learning

  • Pieter Abbeel
  • Aug. 23, 2016

Blogs

• Deep Reinforcement Learning: Pong from Pixels

  • Andrej Karpathy
  • May 31, 2016

• Demystifying Deep Reinforcement Learning

• Simple Reinforcement Learning with Tensorflow Part 0: Q-Learning with Tables and Neural Networks

  • Arthur Juliani
  • Aug 25, 2016

• Before AlphaGo there was TD-Gammon

  • Jim Fleming
  • Apr 4, 2016
  • https://github.com/fomorians/td-gammon

• Learning Policies For Learning Policies — Meta Reinforcement Learning (RL²) in Tensorflow

  • Arthur Juliani
  • Jan 30, 2017
  • https://github.com/awjuliani/Meta-RL

• DeepMind’s PathNet: A Modular Deep Learning Architecture for AGI

  • Carlos E. Perez
  • Feb 4, 2017

• Introduction to reinforcement learning and OpenAI Gym

  • Justin Francis
  • July 13, 2017
  • https://github.com/wagonhelm/Reinforcement-Learning-Introduction/blob/master/Reinforcement%20Learning%20Introduction.ipynb

• AlphaGo Zero - How and Why it Works

  • Tim Wheeler
  • November 2, 2017

• Deep Reinforcement Learning Doesn't Work Yet

  • Feb 14, 2018

Demos

• REINFORCEjs

  • https://github.com/karpathy/reinforcejs

• ConvNetJS Deep Q Learning Demo

  • https://github.com/karpathy/convnetjs

• DeepTraffic

  • http://selfdrivingcars.mit.edu/deeptraffic/

Environment

• ALE

  • http://www.arcadelearningenvironment.org/
  • https://arxiv.org/abs/1207.4708
    • Thu, 19 Jul 2012

• TORCS

  • related
    • https://arxiv.org/abs/1304.1672
      • Fri, 5 Apr 2013
    • vtorcs
    • SnakeOil
    • Gym-TORCS
    • https://github.com/fmirus/torcs-1.3.7
    • TORCS robot tutorial
    • T.O.R.C.S. tutorial
    • http://xed.ch/h/torcs.html

• OpenAI Gym

  • https://gym.openai.com/
  • OpenAI Gym Beta
    • APRIL 27, 2016
  • https://arxiv.org/abs/1606.01540
    • Sun, 5 Jun 2016

• ViZDoom

  • http://vizdoom.cs.put.edu.pl/
  • https://arxiv.org/abs/1605.02097
    • Fri, 6 May 2016
  • related
    • Freedoom
      • https://freedoom.github.io/

• Project Malmö

  • https://www.microsoft.com/en-us/research/project/project-malmo/
  • Project Malmo, which lets researchers use Minecraft for AI research, makes public debut
    • Jul 7, 2016

• Industrial Benchmark

  • https://arxiv.org/abs/1610.03793
    • Wed, 12 Oct 2016
  • https://arxiv.org/abs/1709.09480
    • Wed, 27 Sep 2017

• RLE

  • gym-rle
  • https://arxiv.org/abs/1611.02205
    • Mon, 7 Nov 2016

• TorchCraft

  • https://arxiv.org/abs/1611.00625
    • Tue, 1 Nov 2016
  • StarData

• DeepMind Lab

  • Open-sourcing DeepMind Lab
    • Saturday, 3 December 2016
  • https://arxiv.org/abs/1612.03801
    • Mon, 12 Dec 2016

• OpenAI Universe

  • https://universe.openai.com/
  • Universe
    • DECEMBER 5, 2016

• Roboschool

  • Roboschool
    • MAY 15, 2017

• ParlAI

  • http://parl.ai/
  • https://arxiv.org/abs/1705.06476
    • Thu, 18 May 2017

• ELF: An Extensive, Lightweight and Flexible Platform for Game Research

  • https://arxiv.org/abs/1707.01067
    • Tue, 4 Jul 2017

• PySC2 - StarCraft II Learning Environment

  • https://github.com/Blizzard/s2client-proto
  • DeepMind and Blizzard open StarCraft II as an AI research environment
    • Wednesday, 9 August 2017
  • https://arxiv.org/abs/1708.04782
    • Wed, 16 Aug 2017

• Competitive Multi-Agent Environments

  • https://sites.google.com/view/multi-agent-competition
  • https://arxiv.org/abs/1710.03748
    • 10 Oct 2017

• HoME: a Household Multimodal Environment

  • https://home-platform.github.io/
  • https://arxiv.org/abs/1711.11017
    • 29 Nov 2017

• MINOS: Multimodal Indoor Simulator

  • https://minosworld.github.io/
  • https://arxiv.org/abs/1712.03931
    • 11 Dec 2017

• AI2-THOR: Photorealistic Interactive Environments for AI Agents

  • http://ai2thor.allenai.org/
  • https://arxiv.org/abs/1712.05474
    • 14 Dec 2017

• Ray RLLib

  • https://arxiv.org/abs/1712.09381
    • 26 Dec 2017

• The DeepMind Control Suite and Control Package

  • https://arxiv.org/abs/1801.00690
    • 2 Jan 2018

• House3D: A Rich and Realistic 3D Environment

  • https://arxiv.org/abs/1801.02209
    • 7 Jan 2018

Libraries

• Keras-RL

• rllab

  • https://arxiv.org/abs/1604.06778
    • Fri, 22 Apr 2016

• Unity ML

  • Introducing: Unity Machine Learning Agents
    • September 19, 2017

Codes

Papers

Survey

• Deep Reinforcement Learning: An Overview

  • https://arxiv.org/abs/1701.07274

• A Brief Survey of Deep Reinforcement Learning

  • https://arxiv.org/abs/1708.05866

• Deep Learning for Video Game Playing

  • https://arxiv.org/abs/1708.07902

• A Survey of Monte Carlo Tree Search Methods

  • 2012
  • http://mcts.ai/pubs/mcts-survey-master.pdf
  • https://orb.essex.ac.uk/ce/ce213/MCTS_Survey.pdf

Sites

• mcts.ai
  • Monte Carlo Tree Search (MCTS) research hub