Out-of-Distribution Generalisation with Sequence Models in Offline Multi-Agent Reinforcement Learning
This work presents a principled analysis of zero-shot task generalisation in the offline setting and conducts an extensive empirical investigation into the scaling behaviour governing task diversity, dataset size, and network capacity.
Oussama Hidaoui, Omer Ebead, Ulrich A. Mbou Sob et al.
· 0 citations