A custom MARL (multi-agent reinforcement learning) environment where multiple agents trade against one another (self-play) in a zero-sum continuous double auction. Ray [RLlib] is used for training.

My reproduction of various reinforcement learning algorithms (DQN variants, A3C, DPPO, RND with PPO) in Tensorflow.

This repository contains simple usage examples for basic machine learning libraries. These notebooks are tested in Colab.

My github pages

A simple example of painting color over the lips region based on facial landmark prediction with the Helen dataset, using transfer learning & fine tuning with a 3rd party pretrained model.

Sample CI/CD devops setup of Django & Postgres web app with Travis & Heroku

My attempt to reproduce a water down version of PBT (Population based training) for MARL (Multi-agent reinforcement learning) using DDPPO (Decentralized & distributed proximal policy optimization) …

Sample CI/CD devops setup of Django & Postgres web app with Docker, Travis & Heroku.

Bayesian based machine learning implementations (GMM, VAE & conditional VAE).

Sample setup for custom reinforcement learning environment in Sagemaker. This example uses Proximal Policy Optimization with Ray (RLlib).

Source code for the official Django tutorial (writing your first Django app).