Merge pull request #371 from mwydmuch/master

Add Python Reinforcement Learning category...

README.md

@@ -86,7 +86,8 @@ For a list of free-to-attend meetups and local events, go [here](https://github.
     - [Data Analysis / Data Visualization](#python-data-analysis)
     - [Misc Scripts / iPython Notebooks / Codebases](#python-misc)
     - [Kaggle Competition Source Code](#python-kaggle)
-    - [Neural networks](#python-neural networks)
+    - [Neural Networks](#python-neural-networks)
+    - [Reinforcement Learning](#python-reinforcement-learning)
 - [Ruby](#ruby)
     - [Natural Language Processing](#ruby-nlp)
     - [General-Purpose Machine Learning](#ruby-general-purpose)
@@ -369,7 +370,6 @@ For a list of free-to-attend meetups and local events, go [here](https://github.
 * [Weka](http://www.cs.waikato.ac.nz/ml/weka/) - Weka is a collection of machine learning algorithms for data mining tasks
 * [LBJava](https://github.com/IllinoisCogComp/lbjava/) - Learning Based Java is a modeling language for the rapid development of software systems, offers a convenient, declarative syntax for classifier and constraint definition directly in terms of the objects in the programmer's application.
 
-
 #### Speech Recognition
 * [CMU Sphinx](http://cmusphinx.sourceforge.net/) - Open Source Toolkit For Speech Recognition purely based on Java speech recognition library.
 
@@ -832,7 +832,6 @@ on MNIST digits[DEEP LEARNING]
 * [TFLearn](https://github.com/tflearn/tflearn) - Deep learning library featuring a higher-level API for TensorFlow.
 * [REP](https://github.com/yandex/rep) - an IPython-based environment for conducting data-driven research in a consistent and reproducible way. REP is not trying to substitute scikit-learn, but extends it and provides better user experience.
 * [rgf_python](https://github.com/fukatani/rgf_python) - Python bindings for Regularized Greedy Forest (Tree) Library.
-* [gym](https://github.com/openai/gym) - OpenAI Gym is a toolkit for developing and comparing reinforcement learning algorithms.
 * [skbayes](https://github.com/AmazaspShumik/sklearn-bayes) - Python package for Bayesian Machine Learning with scikit-learn API
 * [fuku-ml](https://github.com/fukuball/fuku-ml) - Simple machine learning library, including Perceptron, Regression, Support Vector Machine, Decision Tree and more, it's easy to use and easy to learn for beginners.
 
@@ -924,17 +923,14 @@ on MNIST digits[DEEP LEARNING]
 * [Introduction to machine learning with scikit-learn](https://github.com/justmarkham/scikit-learn-videos) - IPython notebooks from Data School's video tutorials on scikit-learn.
 * [Practical XGBoost in Python](http://education.parrotprediction.teachable.com/p/practical-xgboost-in-python) - comprehensive online course about using XGBoost in Python
 
-<a name="python-neural networks"/>
+<a name="python-neural-networks"/>
-#### Neural networks
+#### Neural Networks
-* [Neural networks](https://github.com/karpathy/neuraltalk) - NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.
+* [NeuralTalk](https://github.com/karpathy/neuraltalk) - NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.
 * [Neuron](https://github.com/molcik/python-neuron) - Neuron is simple class for time series predictions. It's utilize LNU (Linear Neural Unit), QNU (Quadratic Neural Unit), RBF (Radial Basis Function), MLP (Multi Layer Perceptron), MLP-ELM (Multi Layer Perceptron - Extreme Learning Machine) neural networks learned with Gradient descent or LeLevenberg–Marquardt algorithm.
 * [Data Driven Code](https://github.com/atmb4u/data-driven-code) - Very simple implementation of neural networks for dummies in python without using any libraries, with detailed comments.
 
 <a name="python-kaggle"></a>
 #### Kaggle Competition Source Code
-
-
-
 * [wiki challenge](https://github.com/hammer/wikichallenge) - An implementation of Dell Zhang's solution to Wikipedia's Participation Challenge on Kaggle
 * [kaggle insults](https://github.com/amueller/kaggle_insults) - Kaggle Submission for "Detecting Insults in Social Commentary"
 * [kaggle_acquire-valued-shoppers-challenge](https://github.com/MLWave/kaggle_acquire-valued-shoppers-challenge) - Code for the Kaggle acquire valued shoppers challenge
@@ -953,6 +949,13 @@ on MNIST digits[DEEP LEARNING]
 * [kaggle_acquire-valued-shoppers-challenge](https://github.com/MLWave/kaggle_acquire-valued-shoppers-challenge) - Code for the Kaggle acquire valued shoppers challenge
 * [wine-quality](https://github.com/zygmuntz/wine-quality) - Predicting wine quality
 
+<a name="python-reinforcement-learning"></a>
+#### Reinforcement Learning
+* [DeepMind Lab](https://github.com/deepmind/lab) - DeepMind Lab is a 3D learning environment based on id Software's Quake III Arena via ioquake3 and other open source software. Its primary purpose is to act as a testbed for research in artificial intelligence, especially deep reinforcement learning.
+* [Gym](https://github.com/openai/gym) - OpenAI Gym is a toolkit for developing and comparing reinforcement learning algorithms.
+* [Universe](https://github.com/openai/universe) - Universe is a software platform for measuring and training an AI's general intelligence across the world's supply of games, websites and other applications.
+* [ViZDoom](https://github.com/mwydmuch/ViZDoom) - ViZDoom allows developing AI bots that play Doom using only the visual information (the screen buffer). It is primarily intended for research in machine visual learning, and deep reinforcement learning, in particular.
+
 <a name="ruby"></a>
 ## Ruby