Search Results for author: Arnu Pretorius

Found 26 papers, 13 papers with code

On Diagnostics for Understanding Agent Training Behaviour in Cooperative MARL

no code implementations13 Dec 2023 Wiem Khlifi, Siddarth Singh, Omayma Mahjoub, Ruan de Kock, Abidine Vall, Rihab Gorsane, Arnu Pretorius

Cooperative multi-agent reinforcement learning (MARL) has made substantial strides in addressing the distributed decision-making challenges.

Decision Making Multi-agent Reinforcement Learning

Generalisable Agents for Neural Network Optimisation

no code implementations30 Nov 2023 Kale-ab Tessera, Callum Rhys Tilbury, Sasha Abramowitz, Ruan de Kock, Omayma Mahjoub, Benjamin Rosman, Sara Hooker, Arnu Pretorius

Optimising deep neural networks is a challenging task due to complex training dynamics, high computational requirements, and long training times.

Multi-agent Reinforcement Learning Scheduling

Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs

1 code implementation29 Nov 2023 Andries Smit, Paul Duckworth, Nathan Grinsztajn, Thomas D. Barrett, Arnu Pretorius

In this context, multi-agent debate (MAD) has emerged as a promising strategy for enhancing the truthfulness of LLMs.

Benchmarking

Combinatorial Optimization with Policy Adaptation using Latent Space Search

1 code implementation NeurIPS 2023 Felix Chalumeau, Shikha Surana, Clement Bonnet, Nathan Grinsztajn, Arnu Pretorius, Alexandre Laterre, Thomas D. Barrett

Combinatorial Optimization underpins many real-world applications and yet, designing performant algorithms to solve these complex, typically NP-hard, problems remains a significant research challenge.

Benchmarking Combinatorial Optimization +3

Reduce, Reuse, Recycle: Selective Reincarnation in Multi-Agent Reinforcement Learning

1 code implementation31 Mar 2023 Claude Formanek, Callum Rhys Tilbury, Jonathan Shock, Kale-ab Tessera, Arnu Pretorius

'Reincarnation' in reinforcement learning has been proposed as a formalisation of reusing prior computation from past experiments when training an agent in an environment.

Multi-agent Reinforcement Learning reinforcement-learning

Off-the-Grid MARL: Datasets with Baselines for Offline Multi-Agent Reinforcement Learning

2 code implementations1 Feb 2023 Claude Formanek, Asad Jeewa, Jonathan Shock, Arnu Pretorius

However, offline MARL is still in its infancy and therefore lacks standardised benchmark datasets and baselines typically found in more mature subfields of reinforcement learning (RL).

Multi-agent Reinforcement Learning reinforcement-learning +1

Towards a Standardised Performance Evaluation Protocol for Cooperative MARL

1 code implementation21 Sep 2022 Rihab Gorsane, Omayma Mahjoub, Ruan de Kock, Roland Dubb, Siddarth Singh, Arnu Pretorius

Combining these recommendations, with novel insights from our analysis, we propose a standardised performance evaluation protocol for cooperative MARL.

Decision Making Multi-agent Reinforcement Learning

Universally Expressive Communication in Multi-Agent Reinforcement Learning

1 code implementation14 Jun 2022 Matthew Morris, Thomas D. Barrett, Arnu Pretorius

Allowing agents to share information through communication is crucial for solving complex tasks in multi-agent reinforcement learning.

Graph Learning Multi-agent Reinforcement Learning +2

Causal Multi-Agent Reinforcement Learning: Review and Open Problems

no code implementations12 Nov 2021 St John Grimbly, Jonathan Shock, Arnu Pretorius

This paper serves to introduce the reader to the field of multi-agent reinforcement learning (MARL) and its intersection with methods from the study of causality.

Multi-agent Reinforcement Learning reinforcement-learning +1

On pseudo-absence generation and machine learning for locust breeding ground prediction in Africa

1 code implementation6 Nov 2021 Ibrahim Salihu Yusuf, Kale-ab Tessera, Thomas Tumiel, Zohra Slim, Amine Kerkeni, Sella Nevo, Arnu Pretorius

In this paper, we compare this random sampling approach to more advanced pseudo-absence generation methods, such as environmental profiling and optimal background extent limitation, specifically for predicting desert locust breeding grounds in Africa.

regression

Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel

no code implementations4 Nov 2021 Kevin Eloff, Okko Räsänen, Herman A. Engelbrecht, Arnu Pretorius, Herman Kamper

Multi-agent reinforcement learning has been used as an effective means to study emergent communication between agents, yet little focus has been given to continuous acoustic communication.

Language Acquisition Multi-agent Reinforcement Learning +3

Robust and Scalable SDE Learning: A Functional Perspective

no code implementations ICLR 2022 Scott Cameron, Tyron Cameron, Arnu Pretorius, Stephen Roberts

Stochastic differential equations provide a rich class of flexible generative models, capable of describing a wide range of spatio-temporal processes.

Mava: a research library for distributed multi-agent reinforcement learning in JAX

1 code implementation3 Jul 2021 Ruan de Kock, Omayma Mahjoub, Sasha Abramowitz, Wiem Khlifi, Callum Rhys Tilbury, Claude Formanek, Andries Smit, Arnu Pretorius

Our criteria for such software is that it should be simple enough to use to implement new ideas quickly, while at the same time be scalable and fast enough to test those ideas in a reasonable amount of time.

Decision Making Multi-agent Reinforcement Learning +2

On Optimal Transformer Depth for Low-Resource Language Translation

1 code implementation9 Apr 2020 Elan van Biljon, Arnu Pretorius, Julia Kreutzer

Therefore, by showing that transformer models perform well (and often best) at low-to-moderate depth, we hope to convince fellow researchers to devote less computational resources, as well as time, to exploring overly large models during the development of these systems.

Machine Translation NMT +1

Stabilising priors for robust Bayesian deep learning

no code implementations23 Oct 2019 Felix McGregor, Arnu Pretorius, Johan du Preez, Steve Kroon

Bayesian neural networks (BNNs) have developed into useful tools for probabilistic modelling due to recent advances in variational inference enabling large scale BNNs.

Variational Inference

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

no code implementations13 Oct 2019 Arnu Pretorius, Elan van Biljon, Benjamin van Niekerk, Ryan Eloff, Matthew Reynard, Steve James, Benjamin Rosman, Herman Kamper, Steve Kroon

Our results therefore suggest that, in the shallow-to-moderate depth setting, critical initialisation provides zero performance gains when compared to off-critical initialisations and that searching for off-critical initialisations that might improve training speed or generalisation, is likely to be a fruitless endeavour.

On the expected behaviour of noise regularised deep neural networks as Gaussian processes

no code implementations12 Oct 2019 Arnu Pretorius, Herman Kamper, Steve Kroon

Recent work has established the equivalence between deep neural networks and Gaussian processes (GPs), resulting in so-called neural network Gaussian processes (NNGPs).

Gaussian Processes

Critical initialisation for deep signal propagation in noisy rectifier neural networks

1 code implementation NeurIPS 2018 Arnu Pretorius, Elan van Biljon, Steve Kroon, Herman Kamper

Simulations and experiments on real-world data confirm that our proposed initialisation is able to stably propagate signals in deep networks, while using an initialisation disregarding noise fails to do so.

Cannot find the paper you are looking for? You can Submit a new open access paper.