Emerging algorithms in DRL.md

• https://github.com/jeanharb/a2oc_delib ***
  A3C style Option-Critic with deliberation cost
  When Waiting is not an Option : Learning Options with a Deliberation Cost Theano+Lasagne

• https://github.com/ikostrikov/pytorch-meta-optimizer ***
  A PyTorch implementation of Learning to learn by gradient descent by gradient descent

• https://github.com/stormmax/irl-imitation
  Implementations of model-based Inverse Reinforcement Learning (IRL) algorithms in python/Tensorflow. Deep MaxEnt, MaxEnt, LPIRL

• https://github.com/jjkke88/RL_toolbox
  reinfore learning tool box, contains trpo, a3c algorithm for continous action space

• https://github.com/tensorflow/agents PPO ****
  Efficient Batched Reinforcement Learning in TensorFlow

• https://github.com/ikostrikov/pytorch-a2c-ppo-acktr ****
  PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO) and Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR).

• https://github.com/hercky/ACER_tf ****
  Implementation for ACER in tensorflow and sonnet by deepmind. SAMPLE EFFICIENT ACTOR-CRITIC WITH EXPERIENCE REPLAY

• https://github.com/GoingMyWay/ProgressiveNeuralNetwor ****
  Progressive Neural Network, based on A3C to train agents on ViZDoom scenarios

• https://github.com/pat-coady/trpo ***
  Proximal Policy Optimization with Generalized Advantage Estimation

• https://github.com/ShangtongZhang/LearningToRun ****
  Highly modularized implementation of popular deep RL algorithms by PyTorch. My principal here is to reuse as much components as I can through different algorithms, use as less tricks as I can and switch easily between classical control tasks like CartPole and Atari games with raw pixel inputs.

• https://github.com/ShangtongZhang/DeepRL ****
  Highly modularized implementation of popular deep RL algorithms by PyTorch Hybrid Reward Architecture (HRA) : Hybrid Reward Architecture for Reinforcement Learning

• https://github.com/nottombrown/rl-teacher ****
  Code for Deep RL from Human Preferences [Christiano et al]. Plus a webapp for collecting human feedback

• https://github.com/floringogianu/categorical-dqn *** Implementation of the Categorical DQN as described in A distributional Perspective on Reinforcement Learning.

• https://github.com/alexis-jacq/Pytorch-DPPO ***
  Pytorch implementation of Distributed Proximal Policy Optimization

• https://github.com/cbfinn/maml_rl ****
  Code for RL experiments in "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"

• https://github.com/andrewliao11/NoisyNet-DQN *****
  https://github.com/Kaixhin/NoisyNet-A3C
  Tensorflow Implementation for "Noisy network for exploration" https://github.com/andrewliao11/Deep-Reinforcement-Learning-Survey/blob/master/papers/Noisy%20Networks%20for%20Exploration.md

• https://github.com/reinforceio/tensorforce *****
  ensorForce: A TensorFlow library for applied reinforcement learning

• https://github.com/facebookresearch/ELF ****
  An End-To-End, Lightweight and Flexible Platform for Game Research

• https://github.com/rz4/DeepDoom-DE ***
  Deep Reinforcement Learning Development Environment for Doom-Bots powered by ViZDoom 1.1.1 and Keras 2.0.
  https://github.com/Atlas-Soft/DeepDoom Navigating 3D Environments Visually Using Distilled Hierarchical Deep Q-Networks

• https://github.com/awjuliani/oreilly-rl-tutorial ****
  Contains Jupyter notebooks associated with the "Deep Reinforcement Learning Tutorial" tutorial given at the O'Reilly 2017 NYC AI Conference.

• https://github.com/Innixma/dex ***
  Continual Learning Toolkit for Reinforcement Learning

• https://github.com/Riashat/Bayesian-Exploration-Deep-RL ***
  Bayesian Uncertainty Exploration in Deep Reinforcement Learning

• https://github.com/jeanharb/option_critic ***
  Implementation of the Option-Critic Architecture on the Atari (ALE) environment

• https://github.com/Nat-D/FeatureControlHRL ***
  Feature Control as Intrinsic Motivation for Hierarchical Reinforcement Learning

• https://github.com/openai/baselines *****
  OpenAI Baselines: high-quality implementations of reinforcement learning algorithms https://github.com/openai/baselines-results

• https://github.com/deepsense-ai/BA3C-CPU  ****
  BA3C-CPU This is the repository containing the source code for our paper concerning playing Atari Games on CPU.

• https://github.com/awjuliani/dfp *****
  This repo hosts the code associated with my O'Reilly article, "Reinforcement Learning for Various, Complex Goals, Using TensorFlow," published on DATE. This the code in this repository contains implementations of Deep Q-Network, and Learning to Act by Predicting the Future.

• https://github.com/dgriff777/rl_a3c_pytorch ****
  This repository includes my implementation with reinforcement learning using Asynchronous Advantage Actor-Critic (A3C) in Pytorch

• https://github.com/village-people/flying-pig ****
  Solving The Malmo Collaborative AI Challenge Early experimentation involved training feed-forward parametrized estimators with DQN, Double DQN (in order to compensate for over-estimation effects early in the training) and policy-gradient based methods. https://github.com/philipjhj/TDP-MSRC-AI-Challenge

• https://github.com/importsysu/malmochallenge *****
  Hierarchical Double Deep Q-Network (HiDDeN) for The Pig Chase Challenge task

• https://github.com/Kaixhin/ACER *****
  Actor-critic with experience replay

• https://github.com/aleju/self-driving-truck ***
  Self-Driving Truck in Euro Truck Simulator 2, trained via Reinforcement Learning

• https://github.com/kimhc6028/pytorch-noreward-rl *****
  pytorch implementation of Curiosity-driven Exploration by Self-supervised Prediction

• https://github.com/dmakian/feudal_networks ****
  An implementation of FeUdal Networks for Hierarchical Reinforcement Learning

• https://github.com/Kaixhin/malmo-challenge ****
  Malmo Collaborative AI Challenge - Team Pig Catcher model-free RL, and simply aim to maximise the reward of our agent. As a baseline we take a DRL algorithm - ACER

• https://github.com/Alfredvc/paac  *****
  Open source implementation of the PAAC algorithm presented in Efficient Parallel Methods for Deep Reinforcement Learning

• https://github.com/facebookresearch/CommNet ****
  Neural network model, suitable for multi-agent learning.

• https://github.com/pathak22/noreward-rl *****
  TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning

• https://github.com/openai/roboschool  ****
  Open-source software for robot simulation, integrated with OpenAI Gym.

• https://github.com/hhexiy/opponent ****
  Implementation for ICML 16 paper "Deep reinforcement learning with opponent modeling"

• https://github.com/LantaoYu/MARL-Papers *****
  Paper list of multi-agent reinforcement learning (MARL)

• https://github.com/deepmind/dnc ****
  A TensorFlow implementation of the Differentiable Neural Computer.

• https://github.com/rlcode/reinforcement-learning *****
  Minimal and Clean Reinforcement Learning Examples

• https://github.com/IntelVCL/DirectFuturePrediction ****
  Code for the paper "Learning to Act by Predicting the Future", Alexey Dosovitskiy and Vladlen Koltun, ICLR 2017

• https://github.com/ShibiHe/Q-Optimality-Tightening ****
  This is my implementation to paper Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening.

• https://github.com/ariseff/overcoming-catastrophic ****
  Implementation of "Overcoming catastrophic forgetting in neural networks" in Tensorflow

• https://github.com/transedward/pytorch-dqn ****
  Deep Q-Learning Network in pytorch

• https://github.com/pkumusic/O-DRL ****
  Object Sensitive Deep Reinforcement Learning. Combining Object Features with Deep Reinforcement Learning methods.

• https://github.com/lifrordi/DeepStack-Leduc ***
  Example implementation of the DeepStack algorithm for no-limit Leduc poker

• https://github.com/rarilurelo/pcl_keras *****
  This is Keras implementation of PCL as described in Bridging the Gap Between Value and Policy Based Reinforcement Learning.

• https://github.com/papoudakis/Asynchronous_RL ****
  This is an implementation of asynchronous reinforcement learning algorithms. This implementation is for gym's doom and atari environment.

• https://github.com/pavitrakumar78/Playing-custom-games-using-Deep-Learning ****
  Implementation of Google's paper on playing atari games using deep learning in python.

• https://github.com/AaronYALai/Reinforcement_Learning_Project  ****** (Keras) Use deep Q-learning to build two Gomoku (Five-in-a-Row) agents playing against each other.

• https://github.com/jingweiz/pytorch-rl *****
  Deep Reinforcement Learning with pytorch & visdom

• https://github.com/samindaa/RLLib ****
  RLLib is a lightweight C++ template library that implements incremental, standard, and gradient temporal-difference learning algorithms in Reinforcement Learning.

• https://github.com/Kaixhin/Easy21 ***
  Assignment from David Silver's Reinforcement Learning course. Coded for clarity, not efficiency. Requires Torch7 with the Moses package.

• https://github.com/kengz/openai_lab *****
  An experimentation framework for Reinforcement Learning using OpenAI Gym, Tensorflow, and Keras.

• https://github.com/rllabmcgill/rlcourse-february-10-Breakend *****
  rlcourse-february-10-Breakend created by GitHub Classroom

• https://github.com/rlpy/rlpy ***
  RLPy is a framework to conduct sequential decision making experiments. The current focus of this project lies on value-function-based reinforcement learning.

• https://github.com/andrewliao11/pytorch-a3c-mujoco ****
  Implement A3C for Mujoco gym envs

• https://github.com/NoobFang/multi-process-UNREAL ****
  Multi-processing implementation of "Reinforcement Learning with Unsupervised Auxiliary Tasks"(UNREAL) with tensorflow

• https://github.com/AI-ON/Multitask-and-Transfer-Learning ****
  Benchmark and build RL architectures that can do multitask and transfer learning.

• https://github.com/ritchieng/the-incredible-pytorch ****
  The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.

• https://github.com/atgambardella/pytorch-es ****
  Evolution Strategies in PyTorch

• https://github.com/aravindr93/robustRL ***
  Robust policy search algorithms which train on model ensembles

• https://github.com/tanmayshankar/RCNN_MDP ***
  This repository is code connected to the paper - T. Shankar, S. K. Dwivedy, P. Guha, Reinforcement Learning via Recurrent Convolutional Neural Networks, published at ICPR 2016.

• https://github.com/carpedm20/text-based-game-rl-tensorflow *****
  Tensorflow implementation of Language Understanding for Text-based Games using Deep Reinforcement Learning.

• https://github.com/openai/evolution-strategies-starter ****
  This is a distributed implementation of the algorithm described in Evolution Strategies as a Scalable Alternative to Reinforcement Learning

• https://github.com/dillonalaird/deep-rl-tensorflow *****
  TensorFlow implementation of Deep Reinforcement Learning papers Deep Learning papers

• https://github.com/florensacc/snn4hrl ***
  Stochastic Neural Networks for Hierarchical Reinforcement Learning

• https://github.com/pkumusic/E-DRL *****
  Exploration Strategies for Deep Reinforcement Learning

• https://github.com/arnomoonens/DeepRL *****
  Combining deep learning and reinforcement learning.

• https://github.com/evancasey/demeter ****
  A library for deep reinforcement learning. Runs on tensorflow.

• https://github.com/evancasey/demeter ****
  A library for deep reinforcement learning. Runs on tensorflow.

• https://github.com/lancelee82/rockrose *****
  Deep Reinforcement Learning Learn. DQN, A3C, UNREAL

• https://github.com/joschu/modular_rl ****
  This repository implements several algorithms: Trust Region Policy Optimization, Proximal Policy Optimization, Cross Entropy Method

• https://github.com/Bifrost-Research/RL-Universe ****
  Implementation of a Reinforcement Learning algorithm for the game Slither.io using the Universe framework from openAI to emulate the game.

• https://github.com/ikostrikov/pytorch-naf *****
  Reimplementation of Continuous Deep Q-Learning with Model-based Acceleration (Normalized Advantage Function).

• https://github.com/djl11/UNREAL *****
  Original from https://github.com/miyosuda/unreal

• https://github.com/yukezhu/tensorflow-reinforce *****
  Implementations of Reinforcement Learning Models in Tensorflow

• https://github.com/sherjilozair/dqn ***
  This is a very basic DQN implementation, which uses OpenAI's gym environment and Keras/Theano neural networks.

• https://github.com/tokb23/dqn ****
  DQN implementation in Keras + TensorFlow + OpenAI Gym

• https://github.com/Islandman93/reinforcepy ***
  Collection of reinforcement learners implemented in python. Mainly including DQN and its variants

• https://github.com/eparisotto/ActorMimic *****
  Train an RL agent to play multiple Atari games at once

• https://github.com/BinRoot/TensorFlow-Book ****
  Accompanying source code for Machine Learning with TensorFlow. Refer to the book for step-by-step explanations.

• https://github.com/yandexdataschool/AgentNet ****
  A lightweight library to build and train deep reinforcement learning and custom recurrent networks using Theano+Lasagne

• https://github.com/vmayoral/basic_reinforcement_learning ****
  An introduction series to Reinforcement Learning (RL) with comprehensive step-by-step tutorials.

• https://github.com/cuayahuitl/SimpleDS ****
  A Simple Deep Reinforcement Learning Dialogue System

• https://github.com/shaneshixiang/rllabplusplus ****
  rllab++ is a framework for developing and evaluating reinforcement learning algorithms, built on rllab.

• https://github.com/mpatacchiola/dissecting-reinforcement-learning ***
  Python code, PDFs and resources for the series of posts on Reinforcement Learning which I published on my personal blog https://mpatacchiola.github.io/blog/

meta-learning

• https://github.com/deepmind/learning-to-learn *****
  Learning to Learn in TensorFlow

• https://github.com/awjuliani/Meta-RL ****
  Implementation of Meta-RL A3C algorithm

A3C

• https://github.com/gliese581gg/A3C_tensorflow **** Tensorflow implementation of 'Asynchronous Methods for Deep Reinforcement Learning'

• https://github.com/gliese581gg/batch-A3C_tensorflow ****
  Modified tensorflow implementation of 'Asynchronous Methods for Deep Reinforcement Learning'

• https://github.com/ssamot/batchA3C ****
  An implementation of A3C in batch mode

• https://github.com/carpedm20/a3c-tensorflow ****
  a3c-tensorflow

• https://github.com/yinchuandong/A3C-keras *****
  A3C-keras

• https://github.com/Itsukara/async_deep_reinforce *****
  Asynchronous deep reinforcement learning + Pseudo-count based reward + On-highscore-learning

• https://github.com/steveKapturowski/async-deep-rl *****
  A Tensorflow based implementation of "Asynchronous Methods for Deep Reinforcement Learning"

• https://github.com/rarilurelo/pytorch_a3c *****
  This is PyTorch implementation of A3C as described in Asynchronous Methods for Deep Reinforcement Learning.

• https://github.com/pfrendl/a3c ****
  Minimal Asynchronous Advantage Actor Critic (A3C) implementation in PyTorch.

• https://github.com/Grzego/async-rl ****
  Variation of "Asynchronous Methods for Deep Reinforcement Learning" with multiple processes generating experience for agent (Keras + Theano + OpenAI Gym)[1-step Q-learning, n-step Q-learning, A3C]

• https://github.com/ebonyclock/deep_rl_vizdoom ****
  Deep reinforcement learning in ViZDoom (using Tensorflow)

• https://github.com/ikostrikov/pytorch-a3c *****
  PyTorch implementation of Asynchronous Advantage Actor Critic (A3C) from "Asynchronous Methods for Deep Reinforcement Learning".

• https://github.com/iankm/FlappyDQL-MultiAgent ****
  deep_q_flappy_mulitplayer

• https://github.com/akolishchak/doom-net-pytorch ****
  Reinforcement learning models in ViZDoom environment

• https://github.com/NVlabs/GA3C ****
  Hybrid CPU/GPU implementation of the A3C algorithm for deep reinforcement learning.

Intrinsically Motivated Reinforcement Learning [Martin?]:

Intrinsically Motivated Reinforcement Learning
Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning
Bayesian Surprise Attracts Human Attention
Variational Information Maximizing Exploration   Unifying Count-Based Exploration and Intrinsic Motivation

PNN & PathNet

• https://github.com/jaesik817/pathnet *****
  Tensorflow Implementation of PathNet: Evolution Channels Gradient Descent in Super Neural Networks

• https://github.com/synpon/prog_nn *****
  A Quick and Dirty Progressive Neural Network written in TensorFlow.

• https://github.com/seann999/progressive_a3c *****
  Code used for an implementation of Progressive Neural Networks

Model-Free Episodic Control

• https://github.com/miyosuda/episodic_control Replicating DeepMind's paper "Model-Free Episodic Control" with VAE on DeepMind Lab environment.

• https://github.com/sudeepraja/Model-Free-Episodic-Control
  Implementation of the Model Free Episodic Control paper by Deep Mind

• https://github.com/ShibiHe/Model-Free-Episodic-Control
  This is the implementation of DQN and Model Free Episodic Control

Market Trade

• https://github.com/deependersingla/deep_trader
  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.

• https://github.com/kh-kim/stock_market_reinforcement_learning ***
  This project provides a stock market environment using OpenGym with Deep Q-learning and Policy Gradient.