Max's repositories

R2D4-RL

Durham University, Dissertation: 1st - 92. Additional Materials and Codebase for the paper: Combining Recent Advances in Reinforcement Learning for Super Mario Bros. - Recurrent Replay Deeper Denser Distributed DQN+ (R2D4+).

WebGL-from-scratch

2nd Year: 1st - 88. A sitting room scene made in WebGL entirely by hand at the most base level possible (no three.js, all models made by hand etc..)

Language:JavaScriptStargazers:4Issues:1Issues:0

CACBCF-Recommender-System

3rd Year: 1st - 92. A Novel Context Aware Restaurant Recommender System Using Content-Boosted Collaborative Filtering (CACBCF).

Language:PythonStargazers:2Issues:1Issues:0

first-order-logic-parser

2nd Year: 1st - 97. A full parser for first order logic, producing a parse tree (png) and a grammar containing all production rules and symbols, along with a log file.

Language:PythonStargazers:2Issues:1Issues:0

pegasus-lightweight-gan

3rd Year: 1st - 104/100. Generative Modelling: Applying GANs to generate out-of-sample inter-class images - "The Mythical Pegasus: A Mysterious Journey".

Language:PythonStargazers:2Issues:1Issues:0

ST-ResNet-Pytorch

Deep Spatio-Temporal Residual Networks for Mobile Location Data Prediction (instead of original Crowd Flow Prediction) - Modified ST-ResNet

Language:PythonStargazers:2Issues:0Issues:0

multicore-n-planet-simulator

3rd Year: 1st - 90. Vectorized and multicore n-body simulators written and extensively optimised in C++ for scalability to millions of particles/planets (using Euler method and Runge-Kutta 2).

Language:C++Stargazers:1Issues:1Issues:0
Language:JavaScriptLicense:Apache-2.0Stargazers:0Issues:0Issues:0

game-of-life

2nd Year: 1st - 97. An implementation of Conway's Game of Life in C on a potentially infinite board size.

Language:CStargazers:0Issues:1Issues:0

machine-learning-project

2nd Year: 1st - 92. A brief project and report on using the OULAD data set to predict and return a CSV of students final grades, from a variety of features, using a Random Forest or an SVC.

Language:PythonStargazers:0Issues:1Issues:0

R2ND4-Gravitar-RL

3rd Year: 1st - 100. A Reinforcement Learning Agent for Gravitar that was initially designed as a non-distributed version of R2D2 and was later developed further.

Language:Jupyter NotebookStargazers:0Issues:1Issues:0

shadowbourne

Custom GitHub Profile

Stargazers:0Issues:1Issues:0

socket-level-message-board

2nd Year: 1st - 91. A brief multithreaded python networking project designed to gain familiarity with networks and client-server interactions at a socket level.

Language:PythonStargazers:0Issues:1Issues:0

ZSL-KG-Plus

MSci Dissertation - Zero-Shot Learning: Towards the Effortless Classification of Mystical Creatures

Stargazers:0Issues:0Issues:0