gandalfvn

async_deep_reinforce

Asynchronous Methods for Deep Reinforcement Learning

bhtsne

Barnes-Hut t-SNE

convnetjs

Deep Learning in Javascript. Train Convolutional Neural Networks (or ordinary ones) in your browser.

deep_q_rl

Theano-based implementation of Deep Q-learning

DQN-tensorflow

Tensorflow implementation of Human-Level Control through Deep Reinforcement Learning

DSR

games

:video_game: A list of popular/awesome videos games, add-ons, maps, etc. hosted on GitHub. Any genre. Any platform. Any engine.

gps

Guided Policy Search

GRAN

GroundedLanguage

ISI Language Grounding and Generation Data

gvgai

This is the framework for the General Video Game Competition - http://www.gvgai.net/

gym

A toolkit for developing and comparing reinforcement learning algorithms.

ISI-CWIC

Learning_ROS_for_Robotics_Programming_2nd_edition

Code and examples for Learning ROS for Robotics Programming - 2nd Edition

matconvnet

MatConvNet: CNNs for MATLAB

MCTS_Futebol

Jogo de futebol utilizando o algoritmo de arvore de busca de Monte Carlo implementado em MatLab

mips

Minimal Policy Search Toolbox

models

Models built with TensorFlow

nmn2

Dynamically predicted neural network structures for multi-domain question answering

PyGamePlayer

Module to help with running learning agents against PyGame games

rllab

rllab is a framework for developing and evaluating reinforcement learning algorithms.

rltorch

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

rosTalker

code to send amazon echo speech to text information to a ros topic

simple_dqn

Simple deep Q-learning agent.

simple_dqn-1

self implemented simple_dqn

tensorflow

Computation using data flow graphs for scalable machine learning

tensorflow_tutorials

From the basics to slightly more interesting applications of Tensorflow

Theano

Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.

torch7

http://torch.ch

vime

Variational Information Maximizing Exploration (VIME) as presented in "Curiosity-driven Exploration in Deep Reinforcement Learning via Bayesian Neural Networks"