djbyrne

CNN-On-The-Cloud-

Code used to build an image classifier for the Fashion MNIST dataset. Built using the Keras library and trained on the FloydHub cloud platform

core_rl

Repo of core reinforcement learning algorithms and explanations using pytorch lightning

DDPG_Reacher

Experiment to implement the DDPG algorithm to train a mechanical arm to reach for a moving target inside the unity ML-Agents virtual environment

DQN_Tensorflow

A jupyter notebook implementing the DQN model in VizDoom

Landing-A-Rocket-With-Simple-Reinforcement-Learning

This repo gives an example of using a simple method of reinforcement learning to beat the Lunar Lander environment. The agent uses a combination of CEM and neural networks using the pytorch library.

MonteCarlo

Implementation of first visit Monte Carlo for prediction and control

MountainCar_TD_Lambda

Solution for mountain car environment using TD Lambda eligibility trace and RBF cells

TD3

Implementation of the TD3 algorithm written in Pytorch

djbyrne/Landing-A-Rocket-With-Simple-Reinforcement-Learning

This repo gives an example of using a simple method of reinforcement learning to beat the Lunar Lander environment. The agent uses a combination of CEM and neural networks using the pytorch library.

djbyrne/MonteCarlo

Implementation of first visit Monte Carlo for prediction and control

djbyrne/TD3

Implementation of the TD3 algorithm written in Pytorch

djbyrne/core_rl

Repo of core reinforcement learning algorithms and explanations using pytorch lightning

djbyrne/CNN-On-The-Cloud-

Code used to build an image classifier for the Fashion MNIST dataset. Built using the Keras library and trained on the FloydHub cloud platform

djbyrne/DDPG_Reacher

Experiment to implement the DDPG algorithm to train a mechanical arm to reach for a moving target inside the unity ML-Agents virtual environment

djbyrne/DQN_Tensorflow

A jupyter notebook implementing the DQN model in VizDoom

djbyrne/Neural-Network-From-Scratch-Tumour-Diagnosis

This notebook goes through how to build a neural network using only numpy. The network classifies tumours, identifying if they are malignant or benign. This notebook uses the Breast Cancer Wisconsin dataset.

djbyrne/SAC

Pytorch implementation of the Soft Actor Critic Algorithm

djbyrne/awesome-prompt-engineering

repo containing useful prompt engineering templates that I use for coding, research and productivity

djbyrne/deep-reinforcement-learning

Repo for the Deep Reinforcement Learning Nanodegree program

djbyrne/FlappyBirdRL

A reinforcement learning environment based on the mobile game "Flappy Bird" built using the Unity ml-agents framework

djbyrne/MADDPG

Final project for the Udacity RL nano degree implementing Multi Agent Deep Deterministic Policy Gradients

djbyrne/acme

A library of reinforcement learning components and agents

djbyrne/adventures_in_cuda

djbyrne/AI_Hack_NIA

Nia is nutrition app using object classification and detection to gives users nutritional information about their meals and if the portion size is correct

djbyrne/DDQN_Navigation

This is my submission for the Udacity navigation project in the Deep Reinforcement Learning Nano Degree

djbyrne/djbyrne.github.io

Personal blog

djbyrne/dm-haiku

JAX-based neural network library

djbyrne/Halite-III

Season 3 of @twosigma's artificial intelligence programming challenge

djbyrne/jumanji

A diverse suite of scalable reinforcement learning environments in JAX

djbyrne/Neural-Network-From-Scratch-Part-2-TensorFlow

This notebook takes the the same dataset used in the previous notebook and it builds a classification network with tensor flow to diagnose cancer tumours.

djbyrne/optax

Optax is a gradient processing and optimization library for JAX.

djbyrne/ptan

PyTorch Agent Net: reinforcement learning toolkit for pytorch

djbyrne/pytorch-lightning

The lightweight PyTorch wrapper for ML researchers. Scale your models. Write less boilerplate

djbyrne/pytorch-lightning-bolts

PyTorch Lightning Bolts is a community contribution for AI/ML researchers.

djbyrne/RL_Workbench

Library containing Pytorch implementations of some of the main RL algorithms. This repo is used for my own learning purposes

djbyrne/templates

Document templates for open-source projects (README, CONTRIBUTING, GitHub templates)

djbyrne/Value-Iteration

Simple implementation of value iteration using the Frozen Lake Environment

djbyrne/xland-minigrid

JAX-accelerated meta-reinforcement learning environments inspired by XLand and MiniGrid 🏎️