StarCraft+: Benchmarking Multi-agent Algorithms in Adversary Paradigm

• URL: http://arxiv.org/abs/2512.16444v1
• Date: Thu, 18 Dec 2025 11:58:10 GMT
• Title: StarCraft+: Benchmarking Multi-agent Algorithms in Adversary Paradigm
• Authors: Yadong Li, Tong Zhang, Bo Huang, Zhen Cui,
• Abstract summary: In this work, we establish a multi-agent algorithm-vs-algorithm environment, named StarCraft II battle arena (SC2BA)<n>Taking StarCraft as infrastructure, the SC2BA environment is specifically created for inter-algorithm adversary.<n>We benchmark classic MARL algorithms in two types of adversarial modes: dual-algorithm paired adversary and multi-algorithm mixed adversary.
• Score: 30.052231743944727
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 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 \href{https://github.com/dooliu/SC2BA}{Github}, and we believe that this work could mark a new step for the MARL field in the coming years.

Related papers

• Decision Making under Imperfect Recall: Algorithms and Benchmarks [77.12503122836422]
  We introduce the first benchmark suite for imperfect-recall decision problems.<n>Our benchmarks capture a variety of problem types, including ones concerning privacy in AI systems.<n>We evaluate the performance of different algorithms for finding first-order optimal strategies in such problems.
  arXiv  Detail & Related papers  (2026-02-16T23:19:01Z)
• SMAC-Hard: Enabling Mixed Opponent Strategy Script and Self-play on SMAC [19.897956357070697]
  We present SMAC-HARD, a novel benchmark to enhance training robustness and evaluation comprehensiveness.<n>SMAC-HARD supports customizable opponent strategies, randomization of adversarial policies, and interfaces for MARL self-play.<n>We conduct extensive evaluations of widely used and state-of-the-art algorithms on SMAC-HARD, revealing the substantial challenges posed by edited and mixed strategy opponents.
  arXiv  Detail & Related papers  (2024-12-23T16:36:21Z)
• RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation [54.707460684650584]
  Large Language Models (LLMs) demonstrate human-level capabilities in dialogue, reasoning, and knowledge retention. Current research addresses this bottleneck by equipping LLMs with external knowledge, a technique known as Retrieval Augmented Generation (RAG) RAGLAB is a modular and research-oriented open-source library that reproduces 6 existing algorithms and provides a comprehensive ecosystem for investigating RAG algorithms.
  arXiv  Detail & Related papers  (2024-08-21T07:20:48Z)
• FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning [25.857375787748715]
  We present FightLadder, a real-time fighting game platform, to empower competitive MARL research. We provide implementations of state-of-the-art MARL algorithms for competitive games, as well as a set of evaluation metrics. We demonstrate the feasibility of this platform by training a general agent that consistently defeats 12 built-in characters in single-player mode.
  arXiv  Detail & Related papers  (2024-06-04T08:04:23Z)
• Provably Efficient Information-Directed Sampling Algorithms for Multi-Agent Reinforcement Learning [50.92957910121088]
  This work designs and analyzes a novel set of algorithms for multi-agent reinforcement learning (MARL) based on the principle of information-directed sampling (IDS) For episodic two-player zero-sum MGs, we present three sample-efficient algorithms for learning Nash equilibrium. We extend Reg-MAIDS to multi-player general-sum MGs and prove that it can learn either the Nash equilibrium or coarse correlated equilibrium in a sample efficient manner.
  arXiv  Detail & Related papers  (2024-04-30T06:48:56Z)
• MARL-LNS: Cooperative Multi-agent Reinforcement Learning via Large Neighborhoods Search [27.807695570974644]
  We propose a general training framework, MARL-LNS, to address issues by training on alternating subsets of agents. We show that our algorithms can automatically reduce at least 10% of training time while reaching the same final skill level as the original algorithm.
  arXiv  Detail & Related papers  (2024-04-03T22:51:54Z)
• JaxMARL: Multi-Agent RL Environments and Algorithms in JAX [105.343918678781]
  We present JaxMARL, the first open-source, Python-based library that combines GPU-enabled efficiency with support for a large number of commonly used MARL environments. Our experiments show that, in terms of wall clock time, our JAX-based training pipeline is around 14 times faster than existing approaches. We also introduce and benchmark SMAX, a JAX-based approximate reimplementation of the popular StarCraft Multi-Agent Challenge.
  arXiv  Detail & Related papers  (2023-11-16T18:58:43Z)
• Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games [70.19141208203227]
  We consider the problem of decentralized multi-agent reinforcement learning in Markov games. We show that no algorithm attains no-regret in general-sum games when executed independently by all players. We show that our lower bounds hold even for seemingly easier setting in which all agents are controlled by a centralized algorithm.
  arXiv  Detail & Related papers  (2023-03-22T03:28:12Z)
• SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning [45.98103968842858]
  The StarCraft Multi-Agent Challenge (SMAC) is a popular testbed for centralised training with decentralised execution. We show that SMAC lacks the partial observability to require complex *closed-loop* policies. We introduce SMACv2, a new version of the benchmark where scenarios are procedurally generated and require agents to generalise to previously unseen settings.
  arXiv  Detail & Related papers  (2022-12-14T20:15:19Z)
• Cambrian Explosion Algorithm for Multi-Objective Association Rules Mining [5.175050215292647]
  Association rule mining is one of the most studied research fields of data mining. We compare the performances of state-of-the-art meta-heuristics on the association rule mining problem. We propose a new algorithm designed to mine rules efficiently from massive datasets by exploring a large variety of solutions.
  arXiv  Detail & Related papers  (2022-11-23T08:34:05Z)
• MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning Library [82.77446613763809]
  We present MARLlib, a library designed to offer fast development for multi-agent tasks and algorithm combinations. MARLlib can effectively disentangle the intertwined nature of the multi-agent task and the learning process of the algorithm. The library's source code is publicly accessible on GitHub.
  arXiv  Detail & Related papers  (2022-10-11T03:11:12Z)
• Towards General Function Approximation in Zero-Sum Markov Games [126.58493169301012]
  This paper considers two-player zero-sum finite-horizon Markov games with simultaneous moves. Provably efficient algorithms for both decoupled and coordinated settings are developed.
  arXiv  Detail & Related papers  (2021-07-30T15:25:13Z)
• Discovering Multi-Agent Auto-Curricula in Two-Player Zero-Sum Games [31.97631243571394]
  We introduce a framework, LMAC, that automates the discovery of the update rule without explicit human design. Surprisingly, even without human design, the discovered MARL algorithms achieve competitive or even better performance. We show that LMAC is able to generalise from small games to large games, for example training on Kuhn Poker and outperforming PSRO.
  arXiv  Detail & Related papers  (2021-06-04T22:30:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.