Samuel

Using a paper from Google DeepMind I've developed a new version of the DQN using threads exploration instead of memory replay as explain in here: http://arxiv.org/pdf/1602.01783v1.pdf I used the one-...

Zeta36

Chess reinforcement learning by AlphaGo Zero methods.

Zeta36

Connect4 reinforcement learning by AlphaGo Zero methods.

Zeta36

A simple implementation of MuZero algorithm for connect4 game

Zeta36

Random memory adaptation model inspired by the paper: "Memory-based parameter adaptation (MbPA)"

Zeta36

This is a TensorFlow implementation of the WaveNet generative neural network architecture https://deepmind.com/blog/wavenet-generative-model-raw-audio/ for image generation.

Zeta36

This is a TensorFlow implementation of the WaveNet generative neural network architecture https://deepmind.com/blog/wavenet-generative-model-raw-audio/ for text generation.

Zeta36

A Policy Network in Tensorflow to classify chess moves

Zeta36

UCI chess playing engine derived from Stockfish and LeelaChess Zero

Zeta36