mlsanityData to 14 Oct 2026

StarCraft+: Benchmarking Multi-agent Algorithms in Adversary Paradigm

arXiv 2512.16444 ↗First posted 18 Dec 2025cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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 paired adversary and multi-algorithm mixed adversary, where the former conducts the adversary of pairwise algorithms while the latter focuses on the adversary to multiple behaviors from a group of algorithms. The extensive benchmark experiments exhibit some thought-provoking observations/problems in the effectivity, sensibility and scalability of these completed algorithms. The SC2BA environment as well as reproduced experiments are released in hrefhttps://github.com/dooliu/SC2BAGithub, and we believe that this work could mark a new step for the MARL field in the coming years.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 45 of its 72 references that are in the map. First posted on arXiv 18 Dec 2025.

Builds on

45 of 72 references.

References · 45

  1. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  3. 2016OpenAI Gymcited by 1,736
  4. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  5. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,103
  6. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 942
  7. 2017Counterfactual Multi-Agent Policy Gradientscited by 751
  8. 2019The StarCraft Multi-Agent Challengecited by 597
  9. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 567
  10. 2017AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehiclescited by 523
  11. 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 503
  12. 2020Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 485
33 more
  1. 2019QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learningcited by 379
  2. 2019Emergent Tool Use From Multi-Agent Autocurriculacited by 313
  3. 2017StarCraft II: A New Challenge for Reinforcement Learningcited by 274
  4. 2020QPLEX: Duplex Dueling Multi-Agent Q-Learningcited by 270
  5. 2017A Unified Game-Theoretic Approach to Multiagent Reinforcement Learningcited by 268
  6. 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 263
  7. 2019Google Research Football: A Novel Reinforcement Learning Environmentcited by 260
  8. 2020Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Taskscited by 212
  9. 2016ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learningcited by 179
  10. 2020FACMAC: Factored Multi-Agent Centralised Policy Gradientscited by 178
  11. 2019Mastering Complex Control in MOBA Games with Deep Reinforcement Learningcited by 161
  12. 2020Acme: A Research Framework for Distributed Reinforcement Learningcited by 146
  13. 2020ROMA: Multi-Agent Reinforcement Learning with Emergent Rolescited by 137
  14. 2020RODE: Learning Roles to Decompose Multi-Agent Taskscited by 125
  15. 2022SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learningcited by 122
  16. 2022Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learningcited by 119
  17. 2019CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenariocited by 115
  18. 2020Off-Policy Multi-Agent Decomposed Policy Gradientscited by 98
  19. 2016DeepMind Labcited by 74
  20. 2017MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligencecited by 71
  21. 2021Rethinking the Implementation Tricks and Monotonicity Constraint in Cooperative Multi-Agent Reinforcement Learningcited by 68
  22. 2020Mobile Robot Path Planning in Dynamic Environments through Globally Guided Reinforcement Learningcited by 37
  23. 2020Flatland-RL : Multi-Agent Reinforcement Learning on Trainscited by 32
  24. 2018Pommerman: A Multi-Agent Playgroundcited by 30
  25. 2019If MaxEnt RL is the Answer, What is the Question?cited by 27
  26. 2022MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning Librarycited by 21
  27. 2019Autonomous Navigation via Deep Reinforcement Learning for Resource Constraint Edge Nodes using Transfer Learningcited by 19
  28. 2021The Neural MMO Platform for Massively Multiagent Researchcited by 17
  29. 2018Distributed Cooperative Spectrum Sharing in UAV Networks Using Multi-Agent Reinforcement Learningcited by 12
  30. 2022A Novel Deep Reinforcement Learning Based Automated Stock Trading System Using Cascaded LSTM Networkscited by 12
  31. 2019Multi-Agent Image Classification via Reinforcement Learningcited by 8
  32. 2023Learning Team-Based Navigation: A Review of Deep Reinforcement Learning Techniques for Multi-Agent Pathfindingcited by 6
  33. 2023TVDO: Tchebycheff Value-Decomposition Optimization for Multi-Agent Reinforcement Learningcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024SMAC-Hard: Enabling Mixed Opponent Strategy Script and Self-play on SMAC
  2. 2025HLSMAC: A New StarCraft Multi-Agent Challenge for High-Level Strategic Decision-Making
  3. 2024FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning
  4. 2025A Comprehensive Review of Multi-Agent Reinforcement Learning in Video Games
  5. 2026MARL-BattleGrounds: A Novel JAX-native Benchmark for Heterogeneous and Competitive Multi-agent RL
  6. 2020SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II
  7. 2025An Extended Benchmarking of Multi-Agent Reinforcement Learning Algorithms in Complex Fully Cooperative Tasks
  8. 2024MARL-LNS: Cooperative Multi-agent Reinforcement Learning via Large Neighborhoods Search