Michael-Beukman

ChislRLTrading

DecisionAdapter

Code for the paper Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies (NeurIPS 2023). https://arxiv.org/abs/2310.16686

Evocraft22_PCGNN

Runner up submission for the Minecraft Open-Endedness Challenge at GECCO 2022 (https://evocraft.life/)

HWFC

Code for the paper Hierarchical WaveFunction Collapse (AIIDE 2023)

MCHAMR

Generating Large and Complex Levels by Composing Simple Level Generators (IEEE Transactions on Games): https://arxiv.org/abs/2302.01561

NERTransfer

Investigating transfer learning in low-resourced languages, specifically in a named entity recognition (NER) task (IJCNLP-AACL 2023). http://arxiv.org/abs/2309.05311

PCGNN

Combining NEAT and novelty search to quickly generate diverse video game levels (GECCO 2022). https://arxiv.org/abs/2204.06934

ReMiDi

Code for the paper Refining Minimax Regret for Unsupervised Environment Design (ICML 2024) https://arxiv.org/abs/2402.12284

RobocupGym

Reinforcement Learning inside a 3D soccer simulation

HPC-InterestGroup

University of the Witwatersrand High Performance Computing Interest Group Code, Lectures, Notes & Examples

Michael-Beukman/RobocupGym

Reinforcement Learning inside a 3D soccer simulation

Michael-Beukman/PCGNN

Combining NEAT and novelty search to quickly generate diverse video game levels (GECCO 2022). https://arxiv.org/abs/2204.06934

Michael-Beukman/DecisionAdapter

Code for the paper Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies (NeurIPS 2023). https://arxiv.org/abs/2310.16686

Michael-Beukman/HWFC

Code for the paper Hierarchical WaveFunction Collapse (AIIDE 2023)

Michael-Beukman/Evocraft22_PCGNN

Runner up submission for the Minecraft Open-Endedness Challenge at GECCO 2022 (https://evocraft.life/)

Michael-Beukman/NERTransfer

Investigating transfer learning in low-resourced languages, specifically in a named entity recognition (NER) task (IJCNLP-AACL 2023). http://arxiv.org/abs/2309.05311

Michael-Beukman/ReMiDi

Code for the paper Refining Minimax Regret for Unsupervised Environment Design (ICML 2024) https://arxiv.org/abs/2402.12284

Michael-Beukman/ChislRLTrading

Michael-Beukman/MCHAMR

Generating Large and Complex Levels by Composing Simple Level Generators (IEEE Transactions on Games): https://arxiv.org/abs/2302.01561

Michael-Beukman/bibliorobot

Michael-Beukman/EntelectUniCup2021BugsBuggy

Michael-Beukman/ElementaryCellularAutomata

Michael-Beukman/PythonIntroWorkshop

Michael-Beukman/WaveletRL

Michael-Beukman/3KleinGroup

Michael-Beukman/attentionagent.github.io

Web version of “Neuroevolution of Self-Interpretable Agents” (https://arxiv.org/abs/2003.08165)

Michael-Beukman/BuddyMemoryAllocator

A buddy memory allocator we had to implement for a project in our operating systems class

Michael-Beukman/Craftax

Michael-Beukman/creative-coding

A repository for using code to make cool and beautiful things

Michael-Beukman/curses-game-of-life

Using NCurses to visualise Conway's Game of Life

Michael-Beukman/jax-game-of-life

Jax does arrays fast. Game of life is just a binary array. So - Jax implementation of Game of Life?

Michael-Beukman/JaxLife

An Open-Ended Agentic Simulator

Michael-Beukman/masakhane-mt

Machine Translation for Africa

Michael-Beukman/MLConfigSetup

Michael-Beukman/NERTransfer-Embeddings

Michael-Beukman/obsidian-advanced-slides

Create markdown-based reveal.js presentations in Obsidian

Michael-Beukman/quality-diversity.github.io

Website for Quality-Diversity optimisation algorithms

Michael-Beukman/SFML-Mandelbrot

Michael-Beukman/terminalShenanigans

Michael-Beukman/word-vectors

A repository about multilingual word vectors.