Starcraft+: Benchmarking Multi-agent Algorithms In Adversary Paradigm

Abstract

Deep multi-agent reinforcement learning (MARL) algorithms are booming in the field of collaborative intelligence, and StarCraft multi-agent challenge (SMAC) is widely-used as the benchmark therein. However, imaginary opponents of MARL algorithms are practically configured and controlled in a fixed built-in AI mode, which causes less diversity and versatility in algorithm evaluation. To address this issue, in this work, we establish a multi-agent algorithm-vs-algorithm environment, named StarCraft II battle arena (SC2BA), to refresh the benchmarking of MARL algorithms in an adversary paradigm. Taking StarCraft as infrastructure, the SC2BA environment is specifically created for inter-algorithm adversary with the consideration of fairness, usability and customizability, and meantime an adversarial PyMARL (APyMARL) library is developed with easy-to-use interfaces/modules. Grounding in SC2BA, we benchmark those classic MARL algorithms in two types of adversarial modes: dual-algorithm paire

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyli2025starcraft

Related papers

• Smac-hard: Enabling Mixed Opponent Strategy Script And Self-play On SMAC (2024)0.00
• Smacv2: An Improved Benchmark For Cooperative Multi-agent Reinforcement Learning (2022)5.24
• Transformer-based Value Function Decomposition For Cooperative Multi-agent Reinforcement Learning In Starcraft (2022)8.82
• Benchmarking Multi-agent Deep Reinforcement Learning Algorithms In Cooperative Tasks (2020)0.00
• Fightladder: A Benchmark For Competitive Multi-agent Reinforcement Learning (2024)0.00
• A Comprehensive Review Of Multi-agent Reinforcement Learning In Video Games (2025)5.24
• Benchmarl: Benchmarking Multi-agent Reinforcement Learning (2023)5.58
• Reinforcing Competitive Multi-agents For Playing 'so Long Sucker' (2024)0.00