lbarazza Goto Github PK

banana-collector

Double DQN implementation to solve Unity's Banana Collector Environment

boids

Simulation of two storms of birds with boids

chaoticnotes

Interactive notes to learn dynamical systems theory.

deeplearningvideogames

deepqlearning

DQN with keras and gym

descend-the-gradient

Implementation of gradient descent algorithm in a linear regression problem.

fourier-transform-visual

Visualization of the math behind fourier transforms (made with Processing.py)

kohonen

Simple implementation of the Kohonen self-organizing map for dimensionality reduction

language-domain-extractor

Wikipedia scraper to find semantic correlations between words

latorch

A Python library to convert LaTeX tensor expressions to PyTorch models

lbarazza.github.io

Personal Website about AI and cool thoughts

pong-dqn

Model that learns how to play pong. Using OpenAi's Gym

ppo

Implementation of the Proximal Policy Optimization Algorithm

reacher

DDPG implementation to solve Unity's Reacher Environment

rsa-simple

Simple implementation of the RSA algorithm

snake

Simple Unity implementation of the game Snake

spinningup

An educational resource to help anyone learn deep reinforcement learning.

taxi-v2

Implementation of SARSA, SARSA Max and Expected SARSA that play OpenAI's Taxi-v2

tennis

DDPG for solving a multi-agent environment

tile-coding

Implementation of the Tile Coding algorithm

vpg-pytorch

Minimalistic implementation of Vanilla Policy Gradient with PyTorch