Reinforcement Learning

Efficiently Quantifying Individual Agent Importance in Cooperative MARL

Measuring the contribution of individual agents is challenging in cooperative multi-agent reinforcement learning (MARL). In cooperative …

Omayma Mahjoub, Ruan John de Kock, Siddarth Singh, Wiem Khlifi, Abidine Vall, Kale-ab Tessera, Rihab Gorsane, Arnu Pretorius

How much can change in a year? Revisiting Evaluation in Multi-Agent Reinforcement Learning

Establishing sound experimental standards and rigour is important in any growing field of research. Deep Multi-Agent Reinforcement …

Siddarth Singh, Omayma Mahjoub, Ruan John de Kock, Wiem Khlifi, Abidine Vall, Kale-ab Tessera, Arnu Pretorius

Generalisable Agents for Neural Network Optimisation

We train RL agents (an agent per layer) on simple supervised settings to learn to improve optimisation by taking actions, like adapting the learning rate, and then generalise to more resource-intensive supervised learning tasks.

Kale-ab Tessera, Callum Tilbury, Sasha Abramowitz, Ruan de Kock, Omayma Mahjoub, Benjamin Rosman, Sara Hooker, Arnu Pretorius

Generalisable Agents for Neural Network Optimisation

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

Reincarnation in reinforcement learning has been proposed as a formalisation of reusing prior computation from past experiments when …

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

Mava: a research framework for distributed multi-agent reinforcement learning

A framework for MARL, written in JAX.

Deep Learning Indaba Practicals 2022

A collection of high-quality practicals covering a variety of modern machine learning techniques.

Just-in-Time Sparsity: Learning Dynamic Sparsity Schedules

Sparse neural networks have various benefits such as better efficiency and faster training and inference times, while maintaining the …

Kale-ab Tessera, Chiratidzo Matowe, Arnu Pretorius, Benjamin Rosman, Sara Hooker

Just-in-Time Sparsity: Learning Dynamic Sparsity Schedules

Mava: a research framework for distributed multi-agent reinforcement learning

Breakthrough advances in reinforcement learning (RL) research have led to a surge in the development and application of RL. To support …

Arnu Pretorius, Kale-ab Tessera, Andries P. Smit, Claude Formanek, St John Grimbly, Kevin Eloff, Siphelele Danisa, Lawrence Francis, Jonathan Shock, Herman Kamper, Willie Brink, Herman Engelbrecht, Alexandre Laterre, Karim Beguir

DQN Agent playing Pong

A DQN agent playing pong.