Arnu Pretorius

57 papers A* 12A 4Journal 39Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Putting Data at the Centre of Offline Multi-Agent Reinforcement Learning. J. Data-centric Mach. Learn. Res. Claude Formanek, Louise Beyers, Callum Rhys Tilbury, Jonathan P. Shock, Arnu Pretorius
2025	J	`jnl`	Breaking the Performance Ceiling in Complex Reinforcement Learning requires Inference Strategies. CoRR Félix Chalumeau, Daniel Rajaonarivonivelomanantsoa, Ruan de Kock, Claude Formanek, Sasha Abramowitz, Omayma Mahjoub, Wiem Khlifi, Simon du Toit, Louay Ben Nessir, Refiloe Shabe, Arnol Fokam, Siddarth Singh, Ulrich A. Mbou Sob, Arnu Pretorius
2025	J	`jnl`	InstaGeo: Compute-Efficient Geospatial Machine Learning from Data to Deployment. CoRR Ibrahim Salihu Yusuf, Iffanice Houndayi, Rym Oualha, Mohamed Aziz Cherif, Kobby Panford-Quainoo, Arnu Pretorius
2025	A	`conf`	Is an Exponentially Growing Action Space Really that Bad? Validating a Core Assumption for using Multi-Agent RL. AAMAS Ruan de Kock, Arnu Pretorius, Jonathan P. Shock
2025	A	`conf`	Multi-Agent Reinforcement Learning with Selective State-Space Models. AAMAS Jemma Daniel, Ruan John de Kock, Louay Ben Nessir, Sasha Abramowitz, Omayma Mahjoub, Wiem Khlifi, Juan Claude Formanek, Arnu Pretorius
2025	J	`jnl`	Oryx: a Performant and Scalable Algorithm for Many-Agent Coordination in Offline MARL. CoRR Claude Formanek, Omayma Mahjoub, Louay Ben Nessir, Sasha Abramowitz, Ruan de Kock, Wiem Khlifi, Simon du Toit, Félix Chalumeau, Daniel Rajaonarivonivelomanantsoa, Arnol Fokam, Siddarth Singh, Ulrich A. Mbou Sob, Arnu Pretorius
2025	J	`jnl`	Physics informed Transformer-VAE for biophysical parameter estimation: PROSAIL model inversion in Sentinel-2 imagery. CoRR Prince Mensah, Pelumi Victor Aderinto, Ibrahim Salihu Yusuf, Arnu Pretorius
2025	A*	`conf`	Sable: a Performant, Efficient and Scalable Sequence Model for MARL. ICML Omayma Mahjoub, Sasha Abramowitz, Ruan John de Kock, Wiem Khlifi, Simon du Toit, Jemma Daniel, Louay Ben Nessir, Louise Beyers, Juan Claude Formanek, Liam Clark, Arnu Pretorius
2024	J	`jnl`	A Geospatial Approach to Predicting Desert Locust Breeding Grounds in Africa. CoRR Ibrahim Salihu Yusuf, Mukhtar Opeyemi Yusuf, Kobby Panford-Quainoo, Arnu Pretorius
2024	J	`jnl`	Coordination Failure in Cooperative Offline MARL. CoRR Callum Rhys Tilbury, Claude Formanek, Louise Beyers, Jonathan Shock, Arnu Pretorius
2024	A*	`conf`	Dispelling the Mirage of Progress in Offline MARL through Standardised Baselines and Evaluation. NeurIPS Juan Claude Formanek, Callum Rhys Tilbury, Louise Beyers, Jonathan Shock, Arnu Pretorius
2024	J	`jnl`	Dispelling the Mirage of Progress in Offline MARL through Standardised Baselines and Evaluation. CoRR Claude Formanek, Callum Rhys Tilbury, Louise Beyers, Jonathan Shock, Arnu Pretorius
2024	J	`jnl`	Generative Model for Small Molecules with Latent Space RL Fine-Tuning to Protein Targets. CoRR Ulrich A. Mbou Sob, Qiulin Li, Miguel Arbesú, Oliver Bent, Andries P. Smit, Arnu Pretorius
2024	A*	`conf`	Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX. ICLR Clément Bonnet, Daniel Luo, Donal Byrne, Shikha Surana, Sasha Abramowitz, Paul Duckworth, Vincent Coyette, Laurence Illing Midgley, Elshadai Tegegn, Tristan Kalloniatis, Omayma Mahjoub, Matthew Macfarlane, Andries P. Smit, Nathan Grinsztajn, Raphaël Boige, Cemlyn N. Waters, Mohamed A. Mimouni, Ulrich A. Mbou Sob, Ruan de Kock, Siddarth Singh, Daniel Furelos-Blanco, Victor Le, Arnu Pretorius, Alexandre Laterre
2024	J	`jnl`	Memory-Enhanced Neural Solvers for Efficient Adaptation in Combinatorial Optimization. CoRR Félix Chalumeau, Refiloe Shabe, Noah de Nicola, Arnu Pretorius, Thomas D. Barrett, Nathan Grinsztajn
2024	J	`jnl`	Multi-Agent Reinforcement Learning with Selective State-Space Models. CoRR Jemma Daniel, Ruan de Kock, Louay Ben Nessir, Sasha Abramowitz, Omayma Mahjoub, Wiem Khlifi, Claude Formanek, Arnu Pretorius
2024	J	`jnl`	Performant, Memory Efficient and Scalable Multi-Agent Reinforcement Learning. CoRR Omayma Mahjoub, Sasha Abramowitz, Ruan de Kock, Wiem Khlifi, Simon du Toit, Jemma Daniel, Louay Ben Nessir, Louise Beyers, Claude Formanek, Liam Clark, Arnu Pretorius
2024	J	`jnl`	Putting Data at the Centre of Offline Multi-Agent Reinforcement Learning. CoRR Claude Formanek, Louise Beyers, Callum Rhys Tilbury, Jonathan P. Shock, Arnu Pretorius
2024	A*	`conf`	Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs. ICML Andries P. Smit, Nathan Grinsztajn, Paul Duckworth, Thomas D. Barrett, Arnu Pretorius
2023	J	`jnl`	Are we going MAD? Benchmarking Multi-Agent Debate between Language Models for Medical Q&A. CoRR Andries P. Smit, Paul Duckworth, Nathan Grinsztajn, Kale-ab Abebe Tessera, Thomas D. Barrett, Arnu Pretorius
2023	A*	`conf`	Combinatorial Optimization with Policy Adaptation using Latent Space Search. NeurIPS Félix Chalumeau, Shikha Surana, Clément Bonnet, Nathan Grinsztajn, Arnu Pretorius, Alexandre Laterre, Tom Barrett
2023	J	`jnl`	Combinatorial Optimization with Policy Adaptation using Latent Space Search. CoRR Félix Chalumeau, Shikha Surana, Clément Bonnet, Nathan Grinsztajn, Arnu Pretorius, Alexandre Laterre, Thomas D. Barrett
2023	J	`jnl`	Efficiently Quantifying Individual Agent Importance in Cooperative MARL. CoRR Omayma Mahjoub, Ruan de Kock, Siddarth Singh, Wiem Khlifi, Abidine Vall, Kale-ab Abebe Tessera, Arnu Pretorius
2023	J	`jnl`	Generalisable Agents for Neural Network Optimisation. CoRR Kale-ab Abebe Tessera, Callum Rhys Tilbury, Sasha Abramowitz, Ruan de Kock, Omayma Mahjoub, Benjamin Rosman, Sara Hooker, Arnu Pretorius
2023	J	`jnl`	How much can change in a year? Revisiting Evaluation in Multi-Agent Reinforcement Learning. CoRR Siddarth Singh, Omayma Mahjoub, Ruan de Kock, Wiem Khlifi, Abidine Vall, Kale-ab Abebe Tessera, Arnu Pretorius
2023	J	`jnl`	Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX. CoRR Clément Bonnet, Daniel Luo, Donal Byrne, Shikha Surana, Vincent Coyette, Paul Duckworth, Laurence I. Midgley, Tristan Kalloniatis, Sasha Abramowitz, Cemlyn N. Waters, Andries P. Smit, Nathan Grinsztajn, Ulrich A. Mbou Sob, Omayma Mahjoub, Elshadai Tegegn, Mohamed A. Mimouni, Raphaël Boige, Ruan de Kock, Daniel Furelos-Blanco, Victor Le, Arnu Pretorius, Alexandre Laterre
2023	A*	`conf`	Nonparametric Boundary Geometry in Physics Informed Deep Learning. NeurIPS Scott Alexander Cameron, Arnu Pretorius, Stephen J. Roberts
2023	A	`conf`	Off-the-Grid MARL: Datasets and Baselines for Offline Multi-Agent Reinforcement Learning. AAMAS Claude Formanek, Asad Jeewa, Jonathan Shock, Arnu Pretorius
2023	J	`jnl`	Off-the-Grid MARL: a Framework for Dataset Generation with Baselines for Cooperative Offline Multi-Agent Reinforcement Learning. CoRR Claude Formanek, Asad Jeewa, Jonathan Shock, Arnu Pretorius
2023	J	`jnl`	On Diagnostics for Understanding Agent Training Behaviour in Cooperative MARL. CoRR Wiem Khlifi, Siddarth Singh, Omayma Mahjoub, Ruan de Kock, Abidine Vall, Rihab Gorsane, Arnu Pretorius
2023	J	`jnl`	Scaling multi-agent reinforcement learning to full 11 versus 11 simulated robotic football. Auton. Agents Multi Agent Syst. Andries P. Smit, Herman A. Engelbrecht, Willie Brink, Arnu Pretorius
2023	J	`jnl`	Selective Reincarnation: Offline-to-Online Multi-Agent Reinforcement Learning. CoRR Claude Formanek, Callum Rhys Tilbury, Jonathan Shock, Kale-ab Abebe Tessera, Arnu Pretorius
2022	A*	`conf`	Robust and Scalable SDE Learning: A Functional Perspective. ICLR Scott Alexander Cameron, Tyron Luke Cameron, Arnu Pretorius, Stephen J. Roberts
2022	A*	`conf`	Towards a Standardised Performance Evaluation Protocol for Cooperative MARL. NeurIPS Rihab Gorsane, Omayma Mahjoub, Ruan de Kock, Roland Dubb, Siddarth Singh, Arnu Pretorius
2022	J	`jnl`	Towards a Standardised Performance Evaluation Protocol for Cooperative MARL. CoRR Rihab Gorsane, Omayma Mahjoub, Ruan de Kock, Roland Dubb, Siddarth Singh, Arnu Pretorius
2022	A*	`conf`	Universally Expressive Communication in Multi-Agent Reinforcement Learning. NeurIPS Matthew Morris, Thomas D. Barrett, Arnu Pretorius
2022	J	`jnl`	Universally Expressive Communication in Multi-Agent Reinforcement Learning. CoRR Matthew Morris, Thomas D. Barrett, Arnu Pretorius
2021	J	`jnl`	Causal Multi-Agent Reinforcement Learning: Review and Open Problems. CoRR St John Grimbly, Jonathan Shock, Arnu Pretorius
2021	J	`jnl`	Mava: a research library for distributed multi-agent reinforcement learning in JAX. CoRR Ruan de Kock, Omayma Mahjoub, Sasha Abramowitz, Wiem Khlifi, Callum Rhys Tilbury, Claude Formanek, Andries P. Smit, Arnu Pretorius
2021	J	`jnl`	On pseudo-absence generation and machine learning for locust breeding ground prediction in Africa. CoRR Ibrahim Salihu Yusuf, Kale-ab Abebe Tessera, Thomas Tumiel, Sella Nevo, Arnu Pretorius
2021	J	`jnl`	Robust and Scalable SDE Learning: A Functional Perspective. CoRR Scott Alexander Cameron, Tyron Luke Cameron, Arnu Pretorius, Stephen J. Roberts
2021	J	`jnl`	Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel. CoRR Kevin Eloff, Arnu Pretorius, Okko Räsänen, Herman A. Engelbrecht, Herman Kamper
2020	A*	`conf`	A game-theoretic analysis of networked system control for common-pool resource management using multi-agent reinforcement learning. NeurIPS Arnu Pretorius, Scott Alexander Cameron, Elan Van Biljon, Tom Makkink, Shahil Mawjee, Jeremy du Plessis, Jonathan Shock, Alexandre Laterre, Karim Beguir
2020	J	`jnl`	A game-theoretic analysis of networked system control for common-pool resource management using multi-agent reinforcement learning. CoRR Arnu Pretorius, Scott Alexander Cameron, Elan Van Biljon, Tom Makkink, Shahil Mawjee, Jeremy du Plessis, Jonathan Shock, Alexandre Laterre, Karim Beguir
2020	J	`jnl`	If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks. Pattern Recognit. Lett. Arnu Pretorius, Elan Van Biljon, Benjamin van Niekerk, Ryan Eloff, Matthew Reynard, Steven James, Benjamin Rosman, Herman Kamper, Steve Kroon
2020	—	`conf`	On Optimal Transformer Depth for Low-Resource Language Translation. AfricaNLP Elan Van Biljon, Arnu Pretorius, Julia Kreutzer
2020	J	`jnl`	On the expected behaviour of noise regularised deep neural networks as Gaussian processes. Pattern Recognit. Lett. Arnu Pretorius, Herman Kamper, Steve Kroon
2019	J	`jnl`	If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks. CoRR Arnu Pretorius, Elan Van Biljon, Benjamin van Niekerk, Ryan Eloff, Matthew Reynard, Steven James, Benjamin Rosman, Herman Kamper, Steve Kroon
2019	J	`jnl`	On the expected behaviour of noise regularised deep neural networks as Gaussian processes. CoRR Arnu Pretorius, Herman Kamper, Steve Kroon
2019	J	`jnl`	Stabilising priors for robust Bayesian deep learning. CoRR Felix McGregor, Arnu Pretorius, Johan A. du Preez, Steve Kroon
2019	A	`conf`	Unsupervised Acoustic Unit Discovery for Speech Synthesis Using Discrete Latent-Variable Neural Networks. INTERSPEECH Ryan Eloff, André Nortje, Benjamin van Niekerk, Avashna Govender, Leanne Nortje, Arnu Pretorius, Elan Van Biljon, Ewald van der Westhuizen, Lisa van Staden, Herman Kamper
2019	J	`jnl`	Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks. CoRR Ryan Eloff, André Nortje, Benjamin van Niekerk, Avashna Govender, Leanne Nortje, Arnu Pretorius, Elan Van Biljon, Ewald van der Westhuizen, Lisa van Staden, Herman Kamper
2018	A*	`conf`	Critical initialisation for deep signal propagation in noisy rectifier neural networks. NeurIPS Arnu Pretorius, Elan Van Biljon, Steve Kroon, Herman Kamper
2018	J	`jnl`	Critical initialisation for deep signal propagation in noisy rectifier neural networks. CoRR Arnu Pretorius, Elan Van Biljon, Steve Kroon, Herman Kamper
2018	A*	`conf`	Learning Dynamics of Linear Denoising Autoencoders. ICML Arnu Pretorius, Steve Kroon, Herman Kamper
2018	J	`jnl`	Learning Dynamics of Linear Denoising Autoencoders. CoRR Arnu Pretorius, Steve Kroon, Herman Kamper
2016	—	`conf`	Human Decision Making and Artificial Intelligence: A Comparison in the Domain of Sports Prediction. SAICSIT Arnu Pretorius, Douglas A. Parry