Steven James
Scholar

Steven James

Google Scholar ID: _EJDz50AAAAJ
University of the Witwatersrand
Artificial IntelligenceReinforcement Learning
Citations & Impact
All-time
Citations
797
 
H-index
14
 
i10-index
17
 
Publications
20
 
Co-authors
47
list available
Resume (English only)
Academic Achievements
  • Paper 'Skill-Driven Neurosymbolic State Abstractions' accepted to NeurIPS 2025
  • Paper 'Composition and Zero-Shot Transfer with Lattice Structures in Reinforcement Learning' published in the Journal of Artificial Intelligence Research (JAIR), April 2025
  • Paper 'GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Maps' accepted to NeurIPS 2024
  • Paper 'LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization' accepted to GECCO 2024
  • Paper 'Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning' presented at ICLR 2024