Sasha Abramowitz

Researcher, InstaDeep

Joined

September 2021

Names

Sasha Abramowitz (Preferred)

Emails

****@myuct.ac.za (Confirmed)

****@instadeep.com (Confirmed)

Personal Links

Google Scholar

Career & Education History

Researcher

InstaDeep (instadeep.com)

2022 – Present

MS student

University of Cape Town (myuct.ac.za)

2020 – 2022

Advisors, Relations & Conflicts

PhD Advisor

Geoff Nitschke

2020 – 2022

Expertise

Hierarchical Reinforcement learning

Present

Evolutionary computation

Present

Reinforcement learning

Present

Publications

Multi-Task Sequence Models Generalize in Offline Multi-Agent Reinforcement Learning
Ulrich Armel Mbou Sob, Omer, Oussama Hidaoui, Siddarth Singh, Juan Claude Formanek, Felix Chalumeau, Omayma Mahjoub, Sasha Abramowitz, Ruan John de Kock, Wiem Khlifi, Louay Ben Nessir, Simon Verster Du Toit, Daniel Rajaonarivonivelomanantsoa, Asim Awad Osman, Arnol Manuel Fokam, Refiloe Shabe, Ulrich Paquet, Arnu Pretorius
- Submitted to ICLR 2026
- Readers: Everyone
Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies
Felix Chalumeau, Daniel Rajaonarivonivelomanantsoa, Ruan John de Kock, Juan Claude Formanek, Sasha Abramowitz, Omayma Mahjoub, Wiem Khlifi, Simon Verster Du Toit, Louay Ben Nessir, Refiloe Shabe, Arnol Manuel Fokam, Siddarth Singh, Ulrich Armel Mbou Sob, Arnu Pretorius
- NeurIPS 2025 oral
- Readers: Everyone
Oryx: a Scalable Sequence Model for Many-Agent Coordination in Offline MARL
Juan Claude Formanek, Omayma Mahjoub, Louay Ben Nessir, Sasha Abramowitz, Ruan John de Kock, Wiem Khlifi, Daniel Rajaonarivonivelomanantsoa, Simon Verster Du Toit, Arnol Manuel Fokam, Siddarth Singh, Ulrich Armel Mbou Sob, Felix Chalumeau, Arnu Pretorius
- NeurIPS 2025 poster
- Readers: Everyone
Sable: a Performant, Efficient and Scalable Sequence Model for MARL
Omayma Mahjoub, Sasha Abramowitz, Ruan John de Kock, Wiem Khlifi, Simon Verster Du Toit, Jemma Daniel, Louay Ben Nessir, Louise Beyers, Juan Claude Formanek, Liam Clark, Arnu Pretorius
- ICML 2025 poster
- Readers: Everyone
Performant, Memory Efficient and Scalable Multi-Agent Reinforcement Learning
Omayma Mahjoub, Sasha Abramowitz, Ruan John de Kock, Wiem Khlifi, Simon Verster Du Toit, Jemma Daniel, Louay Ben Nessir, Juan Claude Formanek, Louise Beyers, Liam Clark, Arnu Pretorius
- Submitted to ICLR 2025
- Readers: Everyone
Generalisable Agents for Neural Network Optimisation
Kale-ab Tessera, Callum Rhys Tilbury, Sasha Abramowitz, Ruan John de Kock, Omayma Mahjoub, Benjamin Rosman, Sara Hooker, Arnu Pretorius
- WANT@NeurIPS 2023 Poster
- Readers: Everyone
Generalisable Agents for Neural Network Optimisation
Kale-ab Tessera, Callum Rhys Tilbury, Sasha Abramowitz, Ruan John de Kock, Omayma Mahjoub, Benjamin Rosman, Sara Hooker, Arnu Pretorius
- NeurIPS 2023 Workshop Poster
- Readers: Everyone
Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX
Clément Bonnet, Daniel Luo, Donal John Byrne, Shikha Surana, Sasha Abramowitz, Paul Duckworth, Vincent Coyette, Laurence Illing Midgley, Elshadai Tegegn, Tristan Kalloniatis, Omayma Mahjoub, Matthew Macfarlane, Andries Petrus Smit, Nathan Grinsztajn, Raphael Boige, Cemlyn Neil Waters, Mohamed Ali Ali Mimouni, Ulrich Armel Mbou Sob, Ruan John de Kock, Siddarth Singh et al. (4 additional authors not shown)
- ICLR 2024 poster
- Readers: Everyone
Evolution Strategies as an Alternate Learning method for Hierarchical Reinforcement Learning
Sasha Abramowitz
- Published: 28 Jan 2022, Last Modified: 13 Feb 2023
- ICLR 2022 Submitted
- Readers: Everyone

Co-Authors

View all 42 co-authors