PhD student, University of Cape Town
2 papers at NeurIPS 2025
Using search strategies at inference-time can provide massive performance boost on numerous complex reinforcement learning tasks, within only a couple seconds of execution time.
We extend autoregressive multi-agent sequence models, including Sable and MAT, to the Offline MARL setting and demonstrate that they significanlty outperform current state-of-the-art methods across a diverse set of benchmarks with up to 50 agents.
