Victor Martinez's repositories
stacked_capsule_autoencoders
Forked project from google-research repo
DRL-HC-methods
In this repo I explore the Hill Climbing improvements like adaptative nopise scaling and cross-entropy to use them to solve the enviroment CartPole-v0 from OpenAI-GYM.
Display-Controler-LIBtft144
In this repo I improve the performance of the LIBtft144 controller using numpy and vector operations, and use it to show in real-time the image stream from my raspberry-pi camera on a SPI 144 display
DRL-MC-estimation
In this repo I use the Monte Carlo methods to estimate the value of the different (action, states) pairs in a black jack game, given an heuristic.
DRL-ND-Project_1
This repo contains the solution for the first project of the deep reinforcement learning nano degree from Udacity.
DRL-TD-methods
In this repo I explore the sarsa, sarsa max, and expected sarsa methods to solve RL tasks.