fazega

snake-a2c

Multi process and multi GPU snake training. Using A2C with a CNN.

actor-critic-rl

A multithreaded actor critic model to train an agent in a real-world environment.

bips

Bitcoin Improvement Proposals

bump

conv-game-of-life

fmgdadrr

mapmine

Training a neural network on private browsers accross the Internet.

fmgdadrr-2

gan-rl

A GAN approach to RL. The generator produces actions, and the discriminator is a critic which gives a value.

graphnn

Complete recurrent neural network to model a system's dynamic.

irl-self-paced

IRL (linear, deep) with self-paced learning

leimz

mastodon

Your self-hosted, globally interconnected microblogging community

moby

Moby Project - a collaborative project for the container ecosystem to assemble container-based systems

QuestionTag

Le repository du site :)

vpp