Image Retrieval


Published: 09 Oct 2015

Reinforcement Learning


Demystifying Deep Reinforcement Learning (Part1)

Deep Reinforcement Learning With Neon (Part2)

Deep Reinforcement Learning

Deep Reinforcement Learning

Deep Reinforcement Learning: Pong from Pixels

Deep Reinforcement Learning

Deep Reinforcement Learning

The Nuts and Bolts of Deep RL Research

ML Tutorial: Modern Reinforcement Learning and Video Games

Reinforcement learning explained

Beginner’s guide to Reinforcement Learning & its implementation in Python

Reinforcement Learning on the Web

Deep Q Learning with Keras and Gym

“Deep Reinforcement Learning, Decision Making, and Control

Simple Reinforcement Learning with Tensorflow

Part 0: Q-Learning with Tables and Neural Networks

Part 1 - Two-armed Bandit

Part 2 - Policy-based Agents

Part 3 - Model-Based RL

Part 4: Deep Q-Networks and Beyond

Part 5: Visualizing an Agent’s Thoughts and Actions

Part 6: Partial Observability and Deep Recurrent Q-Networks

Part 7: Action-Selection Strategies for Exploration

Dissecting Reinforcement Learning

REINFORCE tutorial

Deep Q-Learning Recap

Introduction to Reinforcement Learning


Advanced Topics: RL

UCL Course on RL

CS 294: Deep Reinforcement Learning, Fall 2017

CS 294: Deep Reinforcement Learning, Spring 2017

Berkeley CS 294: Deep Reinforcement Learning

(Udacity) Reinforcement Learning - Offered at Georgia Tech as CS 8803

CS229 Lecture notes Part XIII: Reinforcement Learning and Control

Practical_RL: A course in reinforcement learning in the wild

Reinforcement Learning (COMP-762) Winter 2017

**Deep RL Bootcamp - 26-27 August 2017 Berkeley CA**

CMPUT 366: Intelligent Systems and CMPUT 609: Reinforcement Learning & Artificial Intelligence

Deep Reinforcement Learning and Control (Spring 2017, CMU 10703)


Playing Atari with Deep Reinforcement Learning

Deep Learning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree Search Planning

Replicating the Paper “Playing Atari with Deep Reinforcement Learning”

A Tutorial for Reinforcement Learning

Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models

Massively Parallel Methods for Deep Reinforcement Learning

Action-Conditional Video Prediction using Deep Networks in Atari Games

Deep Recurrent Q-Learning for Partially Observable MDPs

Continuous control with deep reinforcement learning

Benchmarking for Bayesian Reinforcement Learning

Deep Reinforcement Learning with Double Q-learning

Giraffe: Using Deep Reinforcement Learning to Play Chess

Human-level control through deep reinforcement learning

Data-Efficient Learning of Feedback Policies from Image Pixels using Deep Dynamical Models

Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning

Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning

MazeBase: A Sandbox for Learning from Games

Learning Simple Algorithms from Examples

Learning Algorithms from Data

Multiagent Cooperation and Competition with Deep Reinforcement Learning

Active Object Localization with Deep Reinforcement Learning

Deep Reinforcement Learning with Attention for Slate Markov Decision Processes with High-Dimensional States and Actions

How to Discount Deep Reinforcement Learning: Towards New Dynamic Strategies

State of the Art Control of Atari Games Using Shallow Reinforcement Learning

Angrier Birds: Bayesian reinforcement learning

Prioritized Experience Replay

Dueling Network Architectures for Deep Reinforcement Learning

Asynchronous Methods for Deep Reinforcement Learning

Graying the black box: Understanding DQNs

Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks

Value Iteration Networks

Insights in Reinforcement Learning

Using Deep Q-Learning to Control Optimization Hyperparameters

Continuous Deep Q-Learning with Model-based Acceleration

Deep Reinforcement Learning from Self-Play in Imperfect-Information Games

Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation

Benchmarking Deep Reinforcement Learning for Continuous Control

Terrain-Adaptive Locomotion Skills Using Deep Reinforcement Learning

Hierarchical Reinforcement Learning using Spatio-Temporal Abstractions and Deep Neural Networks

Deep Successor Reinforcement Learning (MIT)

Learning to Communicate with Deep Multi-Agent Reinforcement Learning

Deep Reinforcement Learning with Regularized Convolutional Neural Fitted Q Iteration RC-NFQ: Regularized Convolutional Neural Fitted Q Iteration

Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks

Bayesian Reinforcement Learning: A Survey

Playing FPS Games with Deep Reinforcement Learning

Reset-Free Guided Policy Search: Efficient Deep Reinforcement Learning with Stochastic Initial States

Utilization of Deep Reinforcement Learning for saccadic-based object visual search

Learning to Navigate in Complex Environments

Reinforcement Learning with Unsupervised Auxiliary Tasks

Learning to reinforcement learn

A Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games

Exploration for Multi-task Reinforcement Learning with Deep Generative Models

Neural Combinatorial Optimization with Reinforcement Learning

Loss is its own Reward: Self-Supervision for Reinforcement Learning

Reinforcement Learning Using Quantum Boltzmann Machines

Deep Reinforcement Learning applied to the game Bubble Shooter

Deep Reinforcement Learning: An Overview

Robust Adversarial Reinforcement Learning

Beating Atari with Natural Language Guided Reinforcement Learning

Feature Control as Intrinsic Motivation for Hierarchical Reinforcement Learning

Distral: Robust Multitask Reinforcement Learning

Deep Reinforcement Learning: Framework, Applications, and Embedded Implementations

Robust Deep Reinforcement Learning with Adversarial Attacks

Variational Deep Q Network

On Monte Carlo Tree Search and Reinforcement Learning

Distributed Deep Reinforcement Learning: Learn how to play Atari games in 21 minutes

GAN Q-learning


Reinforcement Learning: A Survey

A Brief Survey of Deep Reinforcement Learning

  • intro: IEEE Signal Processing Magazine, Special Issue on Deep Learning for Image Understanding
  • intro: Imperial College London & Arizona State University
  • arxiv:

Playing Doom

ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning

Deep Reinforcement Learning From Raw Pixels in Doom

Playing Doom with SLAM-Augmented Deep Reinforcement Learning

Reinforcement Learning via Recurrent Convolutional Neural Networks

Shallow Updates for Deep Reinforcement Learning



General_Deep_Q_RL: General deep Q learning framework

Snake: Toy example of deep reinforcement model playing the game of snake

Using Deep Q Networks to Learn Video Game Strategies

qlearning4k: Q-learning for Keras

rlenvs: Reinforcement learning environments for Torch7, inspired by RL-Glue

deep_rl_ale: An implementation of Deep Reinforcement Learning / Deep Q-Networks for Atari games in TensorFlow

Chimp: General purpose framework for deep reinforcement learning

Deep Q Learning for ATARI using Tensorflow

DeepQLearning: A powerful machine learning algorithm utilizing Q-Learning and Neural Networks, implemented using Torch and Lua.

OpenAI Gym: A toolkit for developing and comparing reinforcement learning algorithms

DeeR: DEEp Reinforcement learning framework

KeRLym: A Deep Reinforcement Learning Toolbox in Keras

Pack of Drones: Layered reinforcement learning for complex behaviors

RL Helicopter Game: Q-Learning and DQN Reinforcement Learning to play the Helicopter Game - Keras based!

Playing Mario with Deep Reinforcement Learning

Deep Attention Recurrent Q-Network

Deep Reinforcement Learning in TensorFlow

rltorch: A RL package for Torch that can also be used with openai gym

deep_q_rl: Theano-based implementation of Deep Q-learning


  • intro: This project uses reinforcement learning on stock market and agent tries to learn trading. The goal is to check if the agent can learn to read tape. The project is dedicated to hero in life great Jesse Livermore.
  • github:

dist-dqn:Distributed Reinforcement Learning using Deep Q-Network in TensorFlow

Deep Reinforcement Learning for Keras

RL4J: Reinforcement Learning for the JVM

Teaching Your Computer To Play Super Mario Bros. – A Fork of the Google DeepMind Atari Machine Learning Project

dprl: Deep reinforcement learning package for torch7

Reinforcement Learning for Torch: Introducing torch-twrl

Alpha Toe - Using Deep learning to master Tic-Tac-Toe - Daniel Slater

Tensorflow-Reinforce: Implementation of Reinforcement Learning Models in Tensorflow

deep RL hacking on minecraft with malmo


markovjs: Reinforcement Learning in JavaScript

Deep Q: Deep reinforcement learning with TensorFlow

Deep Q-Learning Network in pytorch

Tensorflow-RL: Implementations of deep RL papers and random experimentation

Minimal and Clean Reinforcement Learning Examples

DeepRL: Highly modularized implementation of popular deep RL algorithms by PyTorch

Autonomous vehicle navigation


Autonomous vehicle navigation based on Deep Reinforcement Learning

Car Racing using Reinforcement Learning

Play Flappy Bird

Using Deep Q-Network to Learn How To Play Flappy Bird

Playing Flappy Bird Using Deep Reinforcement Learning (Based on Deep Q Learning DQN using Tensorflow)

Playing Flappy Bird Using Deep Reinforcement Learning (Based on Deep Q Learning DQN)

MXNET-Scala Playing Flappy Bird Using Deep Reinforcement Learning

Flappy Bird Bot using Reinforcement Learning in Python

Using Keras and Deep Q-Network to Play FlappyBird


Building a Pong playing AI in just 1 hour(plus 4 days training…)

Pong Neural Network(LIVE)

Tips and Tricks



BURLAP: Brown-UMBC Reinforcement Learning and Planning (BURLAP) java code library

  • intro: for the use and development of single or multi-agent planning and learning algorithms and domains to accompany them
  • homepage:

AgentNet: Deep Reinforcement Learning library for humans

Atari Multitask & Transfer Learning Benchmark (AMTLB)

Coach: a python reinforcement learning research framework containing implementation of many state-of-the-art algorithms


A Short Introduction To Some Reinforcement Learning Algorithms

A Painless Q-Learning Tutorial

Reinforcement Learning - Part 1

Reinforcement Learning - Monte Carlo Methods

Q-learning with Neural Networks

Guest Post (Part I): Demystifying Deep Reinforcement Learning

Using reinforcement learning in Python to teach a virtual car to avoid obstacles: An experiment in Q-learning, neural networks and Pygame.

Reinforcement learning in Python to teach a virtual car to avoid obstacles — part 2

Some Reinforcement Learning Algorithms in Python, C++

learning to do laps with reinforcement learning and neural nets

Get a taste of reinforcement learning — implement a tic tac toe agent

Best reinforcement learning libraries?

Super Simple Reinforcement Learning Tutorial

Reinforcement Learning in Python

The Skynet Salesman

Apprenticeship learning using Inverse Reinforcement Learning

Reinforcement Learning and DQN, learning to play from pixels

Deep Learning in a Nutshell: Reinforcement Learning

Write an AI to win at Pong from scratch with Reinforcement Learning

Learning Reinforcement Learning (with Code, Exercises and Solutions)

Deep Reinforcement Learning: Playing a Racing Game

Experimenting with Reinforcement Learning and Active Inference

Deep reinforcement learning, battleship

Deep Learning Research Review Week 2: Reinforcement Learning

Reinforcement Learning: Artificial Intelligence in Game Playing

Artificial Intelligence’s Next Big Step: Reinforcement Learning

Let’s make a DQN

Let’s make a DQN


Reinforcement Learning: State-of-the-Art

  • intro: “The main goal of this book is to present an up-to-date series of survey articles on the main contemporary sub-fields of reinforcement learning. This includes surveys on partially observable environments, hierarchical task decompositions, relational knowledge representation and predictive state representations. Furthermore, topics such as transfer, evolutionary methods and continuous spaces in reinforcement learning are surveyed. In addition, several chapters review reinforcement learning methods in robotics, in games, and in computational neuroscience. In total seventeen different subfields are presented by mostly young experts in those areas, and together they truly represent a state-of-the-art of current reinforcement learning research.”
  • book:

Reinforcement Learning: An Introduction

Reinforcement Learning: An Introduction (Second edition, Draft)

The Self Learning Quant

Reinforcement Learning: An Introduction


Deep Reinforcement Learning Papers

Awesome Reinforcement Learning

Deep Reinforcement Learning Papers

Deep Reinforcement Learning 深度增强学习资源

deep-reinforcement-learning-networks: A list of deep neural network architectures for reinforcement learning tasks

Deep Reinforcement Learning survey

Studying Reinforcement Learning Guide

Reading and Questions

What are the best books about reinforcement learning?

Published: 09 Oct 2015

Recommendation System


Making a Contextual Recommendation Engine


Collaborative Deep Learning for Recommender Systems

Image-based recommendations on styles and substitutes

A Complex Network Approach for Collaborative Recommendation

Session-based Recommendations with Recurrent Neural Networks

Item2Vec: Neural Item Embedding for Collaborative Filtering

Wide & Deep Learning for Recommender Systems

Hybrid Recommender System based on Autoencoders

Parallel Recurrent Neural Network Architectures for Feature-rich Session-based Recommendations

Collaborative Filtering with Recurrent Neural Networks

Deep Neural Networks for YouTube Recommendations

Photo Filter Recommendation by Category-Aware Aesthetic Learning

  • intro: Filter Aesthetic Comparison Dataset (FACD): 28,000 filtered images and 42,240 reliable image pairs with aesthetic comparison annotations
  • arxiv:

Convolutional Matrix Factorization for Document Context-Aware Recommendation

Deep learning for audio-based music recommendation

Ask the GRU: Multi-Task Learning for Deep Text Recommendations

Collaborative Recurrent Autoencoder: Recommend while Learning to Fill in the Blanks

Recurrent Recommender Networks

Deep Learning based Large Scale Visual Recommendation and Search for E-Commerce

What Your Image Reveals: Exploiting Visual Contents for Point-of-Interest Recommendation

Recurrent Neural Networks with Top-k Gains for Session-based Recommendations

On Sampling Strategies for Neural Network-based Collaborative Filtering

Deep Learning based Recommender System: A Survey and New Perspectives

Training Deep AutoEncoders for Collaborative Filtering

Deep Collaborative Autoencoder for Recommender Systems: A Unified Framework for Explicit and Implicit Feedback

Deep Reinforcement Learning for List-wise Recommendations

Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning


Deep learning for music recommendation

Deep learning for music recommendation and generation


Recommending music on Spotify with deep learning

Generating Recommendations at Amazon Scale with Apache Spark and Amazon DSSTNE

Recommending movies with deep learning

Deep Learning Helps iHeartRadio Personalize Music Recommendations

Applying deep learning to Related Pins

Recommendation System Algorithms: Main existing recommendation engines and how they work

Building a Music Recommender with Deep Learning


NNRec: Neural models for Collaborative Filtering

  • intro: Source code for, AutoRec, an autoencoder based model for collaborative filtering. This package also includes implementation of RBM based collaborative filtering model(RBM-CF).
  • github:

Deep learning recommend system with TensorFlow

Deep Learning Recommender System

Keras Implementation of Recommender Systems


Deep Learning for Recommender Systems

Using MXNet for Recommendation Modeling at Scale


Recommender Systems with Deep Learning


Published: 09 Oct 2015

Classification / Recognition


Published: 09 Oct 2015



Published: 09 Oct 2015

Deep Learning Applications


Published: 09 Oct 2015



Published: 09 Oct 2015

Object Detection

Method backbone test size VOC2007 VOC2010 VOC2012 ILSVRC 2013 MSCOCO 2015 Speed
OverFeat           24.3%    
R-CNN AlexNet   58.5% 53.7% 53.3% 31.4%    
R-CNN VGG16   66.0%          
SPP_net ZF-5   54.2%     31.84%    
DeepID-Net     64.1%     50.3%    
NoC 73.3%   68.8%          
Fast-RCNN VGG16   70.0% 68.8% 68.4%   19.7%(@[0.5-0.95]), 35.9%(@0.5)  
MR-CNN 78.2%   73.9%          
Faster-RCNN VGG16   78.8%   75.9%   21.9%(@[0.5-0.95]), 42.7%(@0.5) 198ms
Faster-RCNN ResNet101   85.6%   83.8%   37.4%(@[0.5-0.95]), 59.0%(@0.5)  
YOLO     63.4%   57.9%     45 fps
YOLO VGG-16     66.4%         21 fps
YOLOv2   448x448 78.6%   73.4%   21.6%(@[0.5-0.95]), 44.0%(@0.5) 40 fps
SSD VGG16 300x300 77.2%   75.8%   25.1%(@[0.5-0.95]), 43.1%(@0.5) 46 fps
SSD VGG16 512x512 79.8%   78.5%   28.8%(@[0.5-0.95]), 48.5%(@0.5) 19 fps
SSD ResNet101 300x300         28.0%(@[0.5-0.95]) 16 fps
SSD ResNet101 512x512         31.2%(@[0.5-0.95]) 8 fps
DSSD ResNet101 300x300         28.0%(@[0.5-0.95]) 8 fps
DSSD ResNet101 500x500         33.2%(@[0.5-0.95]) 6 fps
ION     79.2%   76.4%      
CRAFT     75.7%   71.3% 48.5%    
OHEM     78.9%   76.3%   25.5%(@[0.5-0.95]), 45.9%(@0.5)  
R-FCN ResNet50   77.4%         0.12sec(K40), 0.09sec(TitianX)
R-FCN ResNet101   79.5%         0.17sec(K40), 0.12sec(TitianX)
R-FCN(ms train) ResNet101   83.6%   82.0%   31.5%(@[0.5-0.95]), 53.2%(@0.5)  
PVANet 9.0     84.9%   84.2%     750ms(CPU), 46ms(TitianX)
RetinaNet ResNet101-FPN              
Light-Head R-CNN Xception* 800/1200         31.5%@[0.5:0.95] 95 fps
Light-Head R-CNN Xception* 700/1100         30.7%@[0.5:0.95] 102 fps

Published: 09 Oct 2015