Publications

Refereed Publications

GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Maps

2024
M. Nasir, S. James & J. Togelius

Advances in Neural Information Processing Systems

Download paper

LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization

2024
M. Nasir, S. Earle, C. Cleghorn, S. James & J. Togelius

The Genetic and Evolutionary Computation Conference

Download paper

Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning

2024
G. Nangue Tasse, D. Jarvis, S. James & B Rosman

International Conference on Learning Representations

Download paper

MiDaS: A Large-Scale Minecraft Dataset for Non-Natural Image Benchmarking

2024
D. Torpey, M. Parkin, J. Alter, R. Klein, S. James

Journal of Electronic Imaging

Download paper

Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies

2023
M. Beukman, D. Jarvis, R. Klein, S. James & B. Rosman

Advances in Neural Information Processing Systems

Download paper

Synthesizing Navigation Abstractions for Planning with Portable Manipulation Skills

2023
E. Rosen, S. James, S. Orozco, V. Gupta, M. Merlin, S. Tellex & G. Konidaris

Conference on Robot Learning

Download paper

Overlooked Implications of the Reconstruction Loss for VAE Disentanglement

2023
N. Michlo, R. Klein & S. James

Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence

Download paper

Augmentative Topology Agents for Open-ended Learning

2023
M. Nasir, M. Beukman, S. James & C. Cleghorn

The Genetic and Evolutionary Computation Conference Companion

Download paper

Automatic Encoding and Repair of Reactive High-Level Tasks with Learned Abstract Representations

2023
A. Pacheck, S. James, G. Konidaris & H. Kress-Gazit

The International Journal of Robotics Research

Download paper

Hierarchically Composing Level Generators for the Creation of Complex Structures

2023
M. Beukman, M. Fokam, M. Kruger, G. Axelrod, M. Nasir, B. Ingram, B. Rosman & S. James

IEEE Transactions on Games

Download paper

Procedural Content Generation using Neuroevolution and Novelty Search for Diverse Video Game Levels

2022
M. Beukman, C. Cleghorn & S. James

The Genetic and Evolutionary Computation Conference

Download paper

Autonomous Learning of Object-Centric Abstractions for High-Level Planning

2022
S. James, B. Rosman & G. Konidaris

International Conference on Learning Representations

Download paper

Generalisation in Lifelong Reinforcement Learning through Logical Composition

2022
G. Nangue Tasse, S. James & B. Rosman

International Conference on Learning Representations

Download paper

Investigating Transfer Learning in Graph Neural Networks

2022
N. Kooverjee, S. James & T. van Zyl

Electronics

Download paper

A Boolean Task Algebra for Reinforcement Learning

2020
G. Nangue Tasse, S. James & B. Rosman

Advances in Neural Information Processing Systems

Download paper

Learning Portable Representations for High-Level Planning

2020
S. James, B. Rosman & G. Konidaris

Proceedings of the Thirty-seventh International Conference on Machine Learning

Download paper

If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks

2020
A. Pretorius, E. van Biljon, B. van Niekerk, R. Eloff, M. Reynard, S. James, B. Rosman, H. Kamper & S. Kroon

Pattern Recognition Letters, Elsevier

Download paper

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

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

Local Publications (Refereed)

Combining Evolutionary Search with Behaviour Cloning for Procedurally Generated Content

2022
N. Muir & S. James

Proceedings of 43rd Conference of the South African Institute of Computer Scientists and Information Technologists

Download paper

Quantisation and Pruning for Neural Network Compression and Regularisation

2020
K. Paupamah, S. James & R. Klein

Proceedings of the 2020 SAUPEC/RobMech/PRASA Conference

Download paper

Learning Options from Demonstration using Skill Segmentation

2020
M. Cockroft, S. Mawjee, S. James & P. Ranchod

Proceedings of the 2020 SAUPEC/RobMech/PRASA Conference

Download paper

Inter- and Intra-domain Knowledge Transfer for Related Tasks in Deep Character Recognition

2020
N. Kooverjee, S. James & T. van Zyl

Proceedings of the 2020 SAUPEC/RobMech/PRASA Conference

Download paper

Workshops, Symposia & Tech Reports

Optimal Task Generalisation in Cooperative Multi-Agent Reinforcement Learning

2024
S. Rosen, A. Njupoun, G. Nangue Tasse, S. James & B. Rosman

Coordination and Cooperation in Multi-Agent Reinforcement Learning Workshop at RLC

Download paper

ROSARL: Reward-Only Safe Reinforcement Learning

2024
G. Nangue Tasse, T. Love, M. Nemecek, S. James & B. Rosman

Reinforcement Learning Safety Workshop at RLC

Download paper

MinePlanner: A Benchmark for Long-Horizon Planning in Large Minecraft Worlds

2024
W. Hill, I. Liu, A. De Mello Koch, D. Harvey, N. Kumar, G. Konidaris, S. James

ICAPS Workshop on the International Planning Competition

Download paper

Counting Reward Automata: Sample Efficient Reinforcement Learning Through The Exploitation of Reward Function Structure

2024
T. Bester, B. Rosman, S. James & G. Nangue Tasse

Workshop on Neuro-Symbolic Learning and Reasoning in the Era of Large Language Models at AAAI

Download paper

End-to-End Learning to Follow Language Instructions with Compositional Policies

2022
V. Cohen, G. Nangue Tasse, N. Gopalan, S. James, R. Mooney & B. Rosman

Workshop on Language and Robotics at CoRL

Download paper

Facilitating Safe Sim-to-Real through Simulator Abstraction and Zero-shot Task Composition

2022
T. Love, D. Jarvis, G. Nangue Tasse, B. Ingram, S.James & B. Rosman

Lifelong Learning of High-level Cognitive and Reasoning Skills Workshop @ IROS

Download paper

World Value Functions: Knowledge Representation for Learning and Planning

2022
G. Nangue Tasse, B. Rosman & S. James

Bridging the Gap Between AI Planning and Reinforcement Learning Workshop at ICAPS

Download paper

World Value Functions: Knowledge Representation for Multitask Reinforcement Learning

2022
G. Nangue Tasse, S. James, B. Rosman

The Multi-disciplinary Conference on Reinforcement Learning and Decision Making

Download paper

Adaptive Online Value Function Approximation with Wavelets

2022
M. Beukman, M. Mitchley, D. Wookey, S. James, G. Konidaris

The Multi-disciplinary Conference on Reinforcement Learning and Decision Making

Download paper

Learning Abstract and Transferable Representations for Planning

2022
S. James, B. Rosman, G. Konidaris

The Multi-disciplinary Conference on Reinforcement Learning and Decision Making

Download paper

Accounting for the Sequential Nature of States to Learn Representations in Reinforcement Learning

2022
N. Michlo, D. Jarvis, R. Klein, S. James

The Multi-disciplinary Conference on Reinforcement Learning and Decision Making

Download paper

Towards Objective Metrics for Procedurally Generated Video Game Levels

2022
M. Beukman, S. James, C. Cleghorn

arXiv preprint arXiv:2201.10334

Download paper

Generalisation in Lifelong Reinforcement Learning through Logical Composition

2021
G. Nangue Tasse, S. James, B. Rosman

NeurIPS Deep Reinforcement Learning Workshop

Download paper

Learning to Follow Language Instructions with Compositional Policies

2021
V. Cohen, G. Nangue Tasse, N. Gopalan, S. James, M. Gombolay, B. Rosman

AAAI Fall Symposium on AI for Human-Robot Interaction

Download paper

Learning Object-Centric Representations for High-Level Planning in Minecraft

2020
S. James, B. Rosman & G. Konidaris

Object-Oriented Learning (OOL): Perception, Representation, and Reasoning. Workshop at ICML.

Download paper

Logical Composition for Lifelong Reinforcement Learning

2020
G. Nangue Tasse, S. James & B. Rosman

4th Lifelong Learning Workshop at ICML 2020

Download paper

A Boolean Task Algebra for Reinforcement Learning

2020
G. Nangue Tasse, S. James & B. Rosman

Beyond "Tabula Rasa" in Reinforcement Learning (BeTR-RL): Agents that remember, adapt, and generalize. Workshop at ICLR.

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 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