의사결정RL: 파트6

Simple Reinforcement Learning with Tensorflow Part 0: Q-Learning with Tables and Neural Networks

https://medium.com/emergent-future/simple-reinforcement-learning-with-tensorflow-part-0-q-learning-with-tables-and-neural-networks-d195264329d0#.nmwryydck

Deep Reinforcement Learning for Dialogue Generation - 

https://arxiv.org/abs/1606.01541

1. Introduction

http://nbviewer.jupyter.org/github/psygrammer/dprl/blob/master/part6/RLADS/ch01/01_Introduction.ipynb

2. Background

http://nbviewer.jupyter.org/github/psygrammer/dprl/blob/master/part6/RLADS/ch02/02_Background.ipynb

Hybrid computing using a neural network with dynamic external memory

http://nbviewer.jupyter.org/github/psygrammer/psymovie/blob/master/part2/sp/DNC/Hybrid_computing_using_a_neural_network_with_dynamic_external_memory.ipynb

[16] ATTENTION AND MEMORY IN DEEP LEARNING AND NLP - 

http://www.wildml.com/2016/01/attention-and-memory-in-deep-learning-and-nlp/

Deep Learning for Computer Vision: Attention Models (UPC 2016) - 

http://www.slideshare.net/xavigiro/deep-learning-for-computer-vision-attention-models-upc-2016

Hybrid computing using a neural network with dynamic external memory

https://tensorflowkorea.files.wordpress.com/2016/10/2016-graves.pdf

Deep Q-learning for Stock Trading

http://hallvardnydal.github.io/new_posts/2015-07-21-deep_q/

(관련 코드) https://github.com/deependersingla/deep_trader