Steve(n) James

PhD Candidate and Associate Lecturer, University of the Witwatersrand
I'm a PhD student at the University of the Witwatersrand in Johannesburg, South Africa, where I've spent my entire academic career. I'm also part of the RAIL Lab research group. My research interests revolve around artificial intelligence, and reinforcement learning in particular. I'm currently interested in developing agents capable of learning symbolic state representations that can be transferred between tasks. I count myself extremely fortunate to be supervised by George Konidaris and Benjamin Rosman.

Latest News

Our paper, Composing Value Functions in Reinforcement Learning, was accepted to the 2019 International Conference on Machine Learning.

We recently organised the Deep Learning IndabaX Conference, held at the University of KwaZulu-Natal, Durban.

Our paper, Will it Blend? Composing Value Functions in Reinforcement Learning, was accepted for oral presentation to the 2nd Lifelong Learning: A Reinforcement Learning Approach (LLARLA) Workshop at FAIM in Sweden.

Our paper, Learning to Plan with Portable Symbols, was accepted for oral presentation to the 2018 Workshop on Planning and Learning at FAIM in Sweden.

My extended abstract was accepted to the 2018 IJCAI Doctoral Consortium to be held in July in Sweden.

I was one of four people to be awarded a Google Africa PhD Fellowship in 2018, and the first in Machine Learning in Africa.

Latest Blog Posts

Composing Value Functions in Reinforcement Learning

  • 11 May 2019
In this work, we investigate ways an agent can combine existing skills to create novel ones in a manner that is both principled and optimal. We find that by constraining the reward function and tra...