SMACv-2

SMACv-2 is a benchmark dataset used to evaluate multi-agent reinforcement learning algorithms by providing a set of challenging scenarios that require coordination among agents.

Papers using SMACv-2 (7)

Smacv2: An Improved Benchmark For Cooperative Multi-agent Reinforcement Learning2022 · 26 citesSPECTra: Scalable Multi-Agent Reinforcement Learning with Permutation-Free Networks2025 · 2 citesSTAIRS-Former: Spatio-Temporal Attention with Interleaved Recursive Structure Transformer for Offline Multi-task Multi-agent Reinforcement Learning2026Prism: Spectral Parameter Sharing for Multi-Agent Reinforcement Learning2026MACTAS: Self-Attention-Based Inter-Agent Communication in Multi-Agent Reinforcement Learning with Action-Value Function Decomposition2025QTypeMix: Enhancing Multi-Agent Cooperative Strategies through Heterogeneous and Homogeneous Value Decomposition2024 · 8 citesInverse Factorized Q-Learning for Cooperative Multi-agent Imitation Learning2023