mlsanityData to 7 Oct 2026

Two-Bridge: Exclusive Objectives and Extended Horizon StarCraft II Benchmark

arXiv 2603.06608 ↗First posted 19 Feb 2026cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

The research community lacks a middle ground between StarCraft II full game and its mini-games. The full-game's sprawling state-action space renders reward signals sparse and noisy, but in mini-games simple agents saturate performance. This complexity gap hinders steady curriculum design and prevents researchers from experimenting with modern Reinforcement Learning algorithms in RTS environments under realistic compute budgets. To fill this gap, we present the Two-Bridge Map Suite, the first entry in an open-source benchmark series we purposely engineered as an intermediate benchmark to sit between these extremes. By disabling economy mechanics such as resource collection, base building, and fog-of-war, the environment isolates two core tactical skills: long-range navigation and micro-combat. Preliminary experiments show that agents learn coherent maneuvering and engagement behaviors without imposing full-game computational costs. Two-Bridge is released as a lightweight, Gym-compatible wrapper on top of PySC2, with maps, wrappers, and reference scripts fully open-sourced to encourage broad adoption as a standard benchmark.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 42 references that are in the map. First posted on arXiv 19 Feb 2026.

Builds on

31 of 42 references.

References · 31

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  3. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
  4. 2019The StarCraft Multi-Agent Challengecited by 589
  5. 2020Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 475
  6. 2020Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?cited by 281
  7. 2017StarCraft II: A New Challenge for Reinforcement Learningcited by 268
  8. 2020QPLEX: Duplex Dueling Multi-Agent Q-Learningcited by 267
  9. 2020Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Taskscited by 207
  10. 2020Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 197
  11. 2019MAVEN: Multi-Agent Variational Explorationcited by 181
  12. 2019OpenSpiel: A Framework for Reinforcement Learning in Gamescited by 180
19 more
  1. 2020A Closer Look at Invalid Action Masking in Policy Gradient Algorithmscited by 160
  2. 2020ROMA: Multi-Agent Reinforcement Learning with Emergent Rolescited by 135
  3. 2022Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learningcited by 129
  4. 2020RODE: Learning Roles to Decompose Multi-Agent Taskscited by 125
  5. 2022SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learningcited by 118
  6. 2016Playing FPS Games with Deep Reinforcement Learningcited by 95
  7. 2019A Survey of Deep Reinforcement Learning in Video Gamescited by 73
  8. 2021Rethinking the Implementation Tricks and Monotonicity Constraint in Cooperative Multi-Agent Reinforcement Learningcited by 68
  9. 2022Towards a Standardised Performance Evaluation Protocol for Cooperative MARLcited by 48
  10. 2018StarCraft Micromanagement with Reinforcement Learning and Curriculum Transfer Learningcited by 25
  11. 2020SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft IIcited by 22
  12. 2019A Narration-based Reward Shaping Approach using Grounded Natural Language Commandscited by 16
  13. 2018On Reinforcement Learning for Full-length Game of StarCraftcited by 15
  14. 2018TStarBots: Defeating the Cheating Level Builtin AI in StarCraft II in the Full Gamecited by 14
  15. 2022On Efficient Reinforcement Learning for Full-length Game of StarCraft IIcited by 14
  16. 2018Modular Architecture for StarCraft II with Deep Reinforcement Learningcited by 10
  17. 2025Scalable Decision Making for Games of Imperfect Informationcited by 7
  18. 2021Adversary agent reinforcement learning for pursuit-evasioncited by 1
  19. 2025Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning via Incorporating Generalized Human Expertisecited by 1

Built on by

Not cited yet.