3 papers
cs.AI2024
Efficiently Quantifying Individual Agent Importance in Cooperative MARL
Omayma Mahjoub, Ruan de Kock, Siddarth Singh +4
Measuring the contribution of individual agents is challenging in cooperative multi-agent reinforcement learning (MARL). In cooperative MARL, team performance is typically inferred…
cs.AI2024
How much can change in a year? Revisiting Evaluation in Multi-Agent Reinforcement Learning
Siddarth Singh, Omayma Mahjoub, Ruan de Kock +4
Establishing sound experimental standards and rigour is important in any growing field of research. Deep Multi-Agent Reinforcement Learning (MARL) is one such nascent field. Althou…
cs.AI2023
The challenge of redundancy on multi-agent value factorisation
Siddarth Singh, Benjamin Rosman
In the field of cooperative multi-agent reinforcement learning (MARL), the standard paradigm is the use of centralised training and decentralised execution where a central critic c…