Curriculum Vitae

Download PDF Version

Research Interests

I am super passionate about artificial intelligence and, more specifically, reinforcement learning. In particular, I am interested in designing agents capable of acting in a wide variety of environments. My current research focuses on autonomously learning hierarchies of abstractions that can be transferred between tasks. This parallels the way humans are able to transfer abstract concepts from one task to another in the form of symbolic representations.

Work Experience

Associate Lecturer

University of the Witwatersrand
2017 - Present

Lectured COMS1018A: Introduction to Algorithms & Programming, consisting of ±350 students.

Sessional Lecturer

University of the Witwatersrand
2017

Lectured COMS1018: Introduction to Algorithms & Programming, consisting of ±250 students.

Android Developer

Touchsides
2015 - 2016

Responsible for delivering Android applications related to the insurance industry, and integrating said applications into the existing backend and proprietary hardware systems.

Developer

Associated Computer Solutions
2014 - 2017

Part of a small R&D team responsible for rewriting components of an ERP suite, including replacing the existing Telnet connection to the server with SSL, as well as providing a mechanism for session recovery should the connection be lost. Also responsible for rewriting the entire front-end in JavaFX to be used on multiple platforms.

Tutor

University of the Witwatersrand
2012 - 2014

Responsible for setting and conducting tutorials and lab sessions, as well as marking test scripts.

Publications

Composing Value Functions in Reinforcement Learning

2019
B. van Niekerk, S. James, A. Earle & B. Rosman

Proceedings of the Thirty-sixth International Conference on Machine Learning

Download paper

Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces

2019
C.J. Bester, S. James, & G. Konidaris

arXiv preprint arXiv:1905.04388

Download paper

Learning to Plan with Portable Symbols

2018
S. James, B. Rosman & G. Konidaris

ICML/IJCAI/AAMAS 2018 Workshop on Planning and Learning

Download paper

Will it Blend? Composing Value Functions in Reinforcement Learning

2018
B. van Niekerk, S. James, A. Earle & B. Rosman

The 2nd Lifelong Learning: A Reinforcement Learning Approach (LLARLA) Workshop, FAIM 2018.

Download paper

Learning Portable Symbolic Representations

2018
S. James

2018 IJCAI Doctoral Consortium (extended abstract)

Download paper

An Analysis of Monte Carlo Tree Search

2017
S. James, G. Konidaris & B. Rosman

Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence

Download paper

An Investigation into the Effectiveness of Heavy Rollouts in UCT

2016
S. James, B. Rosman & G. Konidaris

General Intelligence in Game-Playing Agents (GIGA’16) Workshop at IJCAI

Download paper

The Effect of Simulation Bias on Action Selection in Monte Carlo Tree Search

2016
S. James

University of the Witwatersrand (MSc thesis)

Download paper

Education

  • PhD in Computer Science
    University of the Witwatersrand
    2017 - Present
  • MSc in Computer Science (with distinction)
    University of the Witwatersrand
    2014 - 2016
  • BSc (Hons) in Computer Science (with distinction)
    University of the Witwatersrand
    2013
  • BSc in Computer Science and Applied Mathematics (with distinction)
    University of the Witwatersrand
    2010 - 2012

Awards

  • Google PhD Fellowship

    Awarded the 2018 Google Africa PhD Fellowship in the field of Machine Learning.

  • PVT Educational Bursary

    One of two recipients of the PV Tobias Educational Bursary for academically excellent candidates.

  • Chancellor's Gold Medal
    Awarded for the most distinguished graduate of the year.

Language

  • English (Native)
  • Afrikaans (Passable)

Things I Like

  • One true brace style
  • Bitstream Charter
  • Following the gradient
  • Céline Dion
  • Slipknot
  • The word "argillaceous"

Things I Dislike

  • MATLAB
  • Incorrect gerund usage
  • Not following the gradient
  • Squirrels
  • Mispronunciation of "Euler"

Skills

  • Making meaningless, vague bars
  • Sarcasm
  • Redundancy
  • Tautology

Others

  • Artificial Intelligence
  • Reinforcement Learning
  • Transfer Learning
  • Planning
  • Java
  • Python
  • C++11
  • PyTorch
  • Basic Arithmetic