Research Papers

Mava: A new Framework for Distributed Multi-Agent Reinforcement Learning

Arnu Pretorius (InstaDeep Ltd) | Kale-ab Tessera (InstaDeep Ltd) | Andries P. Smit (Stellenbosch University) | Claude Formanek (University of Cape Town) | St John Grimbly (University of Cape Town) | Kevin Eloff (Stellenbosch University) | Siphelele Danisa (University of Cape Town) | Lawrence Francis (InstaDeep Ltd) | Jonathan Shock (University of Cape Town) | Herman Kamper (Stellenbosch University) | Willie Brink (Stellenbosch University) | Herman Engelbrecht (Stellenbosch University) | Alexandre Laterre (InstaDeep Ltd) | Karim Beguir (InstaDeep Ltd)

Jul 2021

Scaling Properties of Deep Residual Networks

Alain-Sam Cohen (InstaDeep Ltd) | Rama Cont (University of Oxford) | Alain Rossier (InstaDeep Ltd & University of Oxford) | Renyuan Xu (University of Oxford)

ICML May 2021

Designing a Prospective COVID-19 Therapeutic with Reinforcement Learning

M. J. Skwark (InstaDeep) | N. L. Carranza (InstaDeep) | T. Pierrot (InstaDeep) | J. Phillips (InstaDeep) | | S. Said (InstaDeep) | A. Laterre (InstaDeep) | A. Kerkeni (InstaDeep) | U. Sahin (BioNTech) | K. Beguir (InstaDeep)

Dec 2020

3D Deep Learning for Biological Function Prediction from Physical Fields

V. Golkov (Technical University of Munich) ¦ M. Skwark (InstaDeep) ¦ A. Mirchev (Technical University of Munich) ¦ G. Dikov (Technical University of Munich) ¦ A. R Geanes (Vanderbilt University) ¦ J. Mendenhall (Vanderbilt University) ¦ J. Meiler (Vanderbilt University) ¦ D. Cremers (TU Munich)

Oct 2020

A game-theoretic analysis of networked system control for common-pool resource management using multi-agent reinforcement learning

A. Pretorius | T. Makkink | J. Shock | S. Cameron | S. Mawjee | A. Laterre | E. Van Biljon | J. Du Plessis | K. Beguir

Sep 2020

AlphaNPI-X: Learning Compositional Neural Programs for Continuous Control

T. Pierrot | N. Perrin | F. Behbahani | A. Laterre | O. Sigaud | K. Beguir | N. De Freitas

Jul 2020

InstaDeep researchers contribute to the Masakhane project and paper

I. Orife, J. Kreutzer, B. Sibanda, D. Whitenack, K. Siminyu, L. Martinus, J. T. Ali, J. Abbott, | V. Marivate, S. Kabongo, M. Meressa, E. Murhabazi, O. Ahia, E. van Biljon, A. Ramkilowan, A. Akinfaderin, | A. Öktem, W. Akin, G. Kioko, K. Degila, H. Kamper, B. Dossou, C. Emezue, K. Ogueji, A. Bashir

Mar 2020

Towards Compositionality in Deep Reinforcement Learning

T. Pierrot, G. Ligner, S. Reed, O. Sigaud, N. Perrin, A. Laterre, D. Kas, K. Beguir, N. de Freitas

Jun 2019

Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization

A. Laterre,  Y. Fu,  M. K. Jabri,  A-S. Cohen,  D. Kas,  K. Hajjar,  T. S. Dahl,  A. Kerkeni,  K. Beguir

Mar 2019

Explicit Sequence Proximity Models for Hidden State Identification

Anil Kota, Sharath Chandra, Parag Khanna | Torbjørn S. Dahl

Mar 2019