Szymon Sidor

tensorflow-deepq. A deep Q learning demonstration using Google Tensorflow

6.006-2015-notebooks. Jupyter Notebook

tf-adversarial. Adversarial networks in TensorFlow

Simple-Guitar-Tuner. Android app

guided-policy-search. Implementation is mostly based on Sergey Levine work (http://www.eecs.berkeley.edu/~svlevine/).

deeprl. Universal library for deep reinforcement learning.

words. HTML

a3c. Asynchronous Advantage Actor Critic

paperclips. This website went down so mirroring (not my game): http://www.decisionproblem.com/paperclips/

cv. My CV in python and latex

words2. JavaScript

tf_nlp. A small repo with utilities for solving nlp problems

RocAlphaGo. An independent, student-led replication of DeepMind's 2016 Nature publication, "Mastering the game of Go with deep neural networks and tree search" (Nature 529, 484-489, 28 Jan 2016), details of which can be found on their website https://deepmind.com/publications.html.

microgrid. C

openmicrogrid-loadboard. Code for the load board of the microgrid project. Loadboard is controlling the power systems and interfacing with appliances. It also does metering.

angel-hack-team-alfa.

SimulatorZoo. Python

java-jack. Tester for jack

ezai. My blog maybe

crowdexchange.

preprocessor. Preprocessor for files.

acrobot. Android app where a human can try to swing up acrobot.