Steve James

Senior Lecturer, University of the Witwatersrand
I'm a senior lecturer and deputy director of the RAIL Lab research group at the University of the Witwatersrand in Johannesburg, South Africa. My research interests revolve around artificial intelligence, and reinforcement learning in particular. I'm currently interested developing generally intelligent agents capable of learning their own representations of tasks, which can subsequently be used for planning. I count myself extremely fortunate to be have been supervised by George Konidaris and Benjamin Rosman.

Latest News

Our paper, GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Maps, was accepted to the 2024 Conference on Neural Information Processing Systems (NeurIPS).

Our paper, LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization, was accepted to the 2024 Genetic and Evolutionary Computation Conference.

Our paper, Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning, was presented at the 2024 International Conference on Learning Representations (ICLR).

Our paper, Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies, was presented at the 2023 Conference on Neural Information Processing Systems (NeurIPS).

Our paper, Synthesizing Navigation Abstractions for Planning with Portable Manipulation Skills, was presented at the Conference on Robot Learning.