Donal Byrne

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

TD3. Implementation of the TD3 algorithm written in Pytorch

core_rl. Repo of core reinforcement learning algorithms and explanations using pytorch lightning

mlp.c. simple implementation of an MLP model in pure C

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

SAC. Pytorch implementation of the Soft Actor Critic Algorithm

cartpole.c. Simple example of developing an RL environment in pure C

DQN_Tensorflow. A jupyter notebook implementing the DQN model in VizDoom

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

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.

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

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

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

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