Michael Beukman
Scholar

Michael Beukman

Google Scholar ID: CaRgqC4AAAAJ
PhD Student, University of Oxford
Reinforcement LearningProcedural Content Generation
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
334
 
H-index
10
 
i10-index
10
 
Publications
20
 
Co-authors
16
list available
Contact
Emailmbeukman@robots.ox.ac.ukTwitterOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
5 items
Goal-Conditioned Agents that Learn Everything All at Once
2026
Cited
0
Procedural Generation of Algorithm Discovery Tasks in Machine Learning
2026
Cited
0
Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments
2026
Cited
0
An Optimisation Framework for Unsupervised Environment Design
2025
Cited
0
Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks
arXiv.org · 2024
Cited
1
Resume (English only)
Co-authors
16 total
Steven James
Steven James
University of the Witwatersrand
Benjamin Rosman
Benjamin Rosman
Professor at the University of the Witwatersrand, South Africa
Co-author 3
Co-author 3
Branden Ingram
Branden Ingram
Lecturer, University of Witwatersrand
Arnol Manuel Fokam
Arnol Manuel Fokam
University of the Witwatersrand
Muhammad Umair Nasir
Muhammad Umair Nasir
PhD Student at New York University and University of the Witwatersrand
Devon Jarvis
Devon Jarvis
University of the Witwatersrand
Jesujoba Oluwadara Alabi
Jesujoba Oluwadara Alabi
Saarland University