MOOCs 2017-04 yandex-contest/ 2017-03 deepnlp-2017/ deeplearningbook udacity/ 2017-02 Cart-Pole Balancing with Q-Learning Simple Reinforcement Learning with Tensorflow: Part0: Q-Learning Agents Bellman equation Part3: Model-Based RL - [ipynb] Once upon a time ML by Yandex & MIPT