MaMuJoCo
Emerging4papers using it
2026first seen
The 'MAMuJoCo' dataset/benchmark is used to evaluate multi-agent reinforcement learning (MARL) algorithms in the context of coordination tasks within simulated environments.
Papers using MaMuJoCo (4)
- CoFlow: Coordinated Few-Step Flow for Offline Multi-Agent Decision MakingSTAIRS-Former: Spatio-Temporal Attention with Interleaved Recursive Structure Transformer for Offline Multi-task Multi-agent Reinforcement LearningPrism: Spectral Parameter Sharing for Multi-Agent Reinforcement LearningDiffusing to Coordinate: Efficient Online Multi-Agent Diffusion Policies