anhducvu-bot Goto Github PK

alphazero_gomoku

An implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row)

automatic-text-summarization

cohort-one

Repository for the second cohort of the apprenticeship program

front-end-template-flask

gym

A toolkit for developing and comparing reinforcement learning algorithms.

mdn

Mixture density network implemented in PyTorch.

neuralnet-mnist

Using PyTorch to create a fully connected neural network that can classify handwritten digit (using MNIST dataset)

nft-image-generator

prisonersdilemmasimulation

A simulation of the prisoner's dilemma using VBA. Different strategies (random, tit for tat, ...) are used to see which strategy would be better in the long run

q_learning_lunarlander

A DQN agent in Python that can solver the Lunar Lander problem from OpenAI

queque-simulation

Simulating a queueing system using Python

resuneta

mxnet source code for the resuneta semantic segmentation models

rltraininggame

A simple game that let the player train their reinforcement learning agent (using Q Learning) to solve the Taxi-Driver problem from OpenAI Gym

swapping_stuffs

A web app for swapping stuffs

temporal_difference_experiment

Setting up experiments to compare the performance of Temporal Difference learning (reinforcement learning) with the Widrow-Hoff algorithm