StarCraft Multi-Agent Challenge (SMACv-2)

The 'StarCraft Multi-Agent Challenge (SMACv-2)' is a benchmark used to evaluate cooperative multi-agent reinforcement learning algorithms in complex, partially observable environments based on the StarCraft game.

Papers using StarCraft Multi-Agent Challenge (SMACv-2) (9)

Closed-Loop Vision-Language Planning for Multi-Agent Coordination2025JointPPO: Diving Deeper into the Effectiveness of PPO in Multi-Agent Reinforcement Learning2024 · 3 citesPPS-QMIX: Periodically Parameter Sharing for Accelerating Convergence of Multi-Agent Reinforcement Learning2024Heterogeneous Multi-Agent Reinforcement Learning for Zero-Shot Scalable Collaboration2024Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning2024Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models2024SMAC-R1: The Emergence of Intelligence in Decision-Making Tasks2024Offline-to-Online Multi-Agent Reinforcement Learning with Offline Value Function Memory and Sequential Exploration2024SMAC-Hard: Enabling Mixed Opponent Strategy Script and Self-play on SMAC2024