Picture for Arnu Pretorius

Arnu Pretorius

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

Mar 31, 2023
Claude Formanek, Callum Rhys Tilbury, Jonathan Shock, Kale-ab Tessera, Arnu Pretorius

Figure 1 for Reduce, Reuse, Recycle: Selective Reincarnation in Multi-Agent Reinforcement Learning

Figure 2 for Reduce, Reuse, Recycle: Selective Reincarnation in Multi-Agent Reinforcement Learning

Figure 3 for Reduce, Reuse, Recycle: Selective Reincarnation in Multi-Agent Reinforcement Learning

Figure 4 for Reduce, Reuse, Recycle: Selective Reincarnation in Multi-Agent Reinforcement Learning

* Accepted as oral presentation at Reincarnating Reinforcement Learning workshop at ICLR 2023

Access Paper or Ask Questions

Towards a Standardised Performance Evaluation Protocol for Cooperative MARL

Sep 21, 2022
Rihab Gorsane, Omayma Mahjoub, Ruan de Kock, Roland Dubb, Siddarth Singh, Arnu Pretorius

Figure 1 for Towards a Standardised Performance Evaluation Protocol for Cooperative MARL

Figure 2 for Towards a Standardised Performance Evaluation Protocol for Cooperative MARL

Figure 3 for Towards a Standardised Performance Evaluation Protocol for Cooperative MARL

Figure 4 for Towards a Standardised Performance Evaluation Protocol for Cooperative MARL

* Published at the 36th Conference on Neural Information Processing Systems (NeurIPS 2022). Website: see https://sites.google.com/view/marl-standard-protocol . 43 Pages, 21 Figures, 8 Tables

Access Paper or Ask Questions

Universally Expressive Communication in Multi-Agent Reinforcement Learning

Jun 14, 2022
Matthew Morris, Thomas D. Barrett, Arnu Pretorius

Figure 1 for Universally Expressive Communication in Multi-Agent Reinforcement Learning

Figure 2 for Universally Expressive Communication in Multi-Agent Reinforcement Learning

Figure 3 for Universally Expressive Communication in Multi-Agent Reinforcement Learning

Figure 4 for Universally Expressive Communication in Multi-Agent Reinforcement Learning

* Submitted to NeurIPS 2022

Access Paper or Ask Questions

Causal Multi-Agent Reinforcement Learning: Review and Open Problems

Dec 01, 2021
St John Grimbly, Jonathan Shock, Arnu Pretorius

Figure 1 for Causal Multi-Agent Reinforcement Learning: Review and Open Problems

Figure 2 for Causal Multi-Agent Reinforcement Learning: Review and Open Problems

Figure 3 for Causal Multi-Agent Reinforcement Learning: Review and Open Problems

* Accepted at Cooperative AI Workshop, NeurIPS 2021

Access Paper or Ask Questions

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

Nov 06, 2021
Ibrahim Salihu Yusuf, Kale-ab Tessera, Thomas Tumiel, Sella Nevo, Arnu Pretorius

Figure 1 for On pseudo-absence generation and machine learning for locust breeding ground prediction in Africa

Figure 2 for On pseudo-absence generation and machine learning for locust breeding ground prediction in Africa

Figure 3 for On pseudo-absence generation and machine learning for locust breeding ground prediction in Africa

Figure 4 for On pseudo-absence generation and machine learning for locust breeding ground prediction in Africa

* AI for Humanitarian Assistance and Disaster Response (AI+HADR) workshop, NeurIPS 2021

Access Paper or Ask Questions

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

Nov 04, 2021
Kevin Eloff, Arnu Pretorius, Okko Räsänen, Herman A. Engelbrecht, Herman Kamper

Figure 1 for Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel

Figure 2 for Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel

Figure 3 for Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel

Figure 4 for Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel

* 12 pages, 6 figures, 3 tables; under review as a conference paper at ICLR 2022

Access Paper or Ask Questions