Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
Dispelling the Mirage of Progress in Offline MARL through Standardised Baselines and Evaluation
Claude Formanek, Callum Rhys Tilbury, Louise Beyers +2
Offline multi-agent reinforcement learning (MARL) is an emerging field with great promise for real-world applications. Unfortunately, the current state of research in offline MARL…
cs.LG2023
Off-the-Grid MARL: Datasets with Baselines for Offline Multi-Agent Reinforcement Learning
Claude Formanek, Asad Jeewa, Jonathan Shock +1
Being able to harness the power of large datasets for developing cooperative multi-agent controllers promises to unlock enormous value for real-world applications. Many important i…