REVIEW 25 cited by
The StarCraft Multi-Agent Challenge
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In the last few years, deep multi-agent reinforcement learning (RL) has become a highly active area of research. A particularly challenging class of problems in this area is partially observable, cooperative, multi-agent learning, in which teams of agents must learn to coordinate their behaviour while conditioning only on their private observations. This is an attractive research area since such problems are relevant to a large number of real-world systems and are also more amenable to evaluation than general-sum problems. Standardised environments such as the ALE and MuJoCo have allowed single-agent RL to move beyond toy domains, such as grid worlds. However, there is no comparable benchmark for cooperative multi-agent RL. As a result, most papers in this field use one-off toy problems, making it difficult to measure real progress. In this paper, we propose the StarCraft Multi-Agent Challenge (SMAC) as a benchmark problem to fill this gap. SMAC is based on the popular real-time strategy game StarCraft II and focuses on micromanagement challenges where each unit is controlled by an independent agent that must act based on local observations. We offer a diverse set of challenge maps and recommendations for best practices in benchmarking and evaluations. We also open-source a deep multi-agent RL learning framework including state-of-the-art algorithms. We believe that SMAC can provide a standard benchmark environment for years to come. Videos of our best agents for several SMAC scenarios are available at: https://youtu.be/VZ7zmQ_obZ0.
Forward citations
Cited by 25 Pith papers
-
DungeonBench: A Benchmark for Rules-Rich Tactical Reasoning in Dungeons & Dragons Combat
DungeonBench scores LLM tactical play on D&D combat, finding frontier policies clear ~80% of single encounters but only 40% of linked multi-encounter days.
-
Assistax: A Multi-Agent Hardware-Accelerated Reinforcement Learning Benchmark for Assistive Robotics
Assistax provides fast JAX-based assistive robotics environments with trainable humanoid partners, and shows current RL baselines have a coordination gap when facing unseen human preferences.
-
TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning
TABX is a JAX-based, GPU-accelerated, configurable multi-agent battle simulator that lets researchers vary units, terrain, and physics to benchmark cooperative MARL algorithms.
-
PillagerBench: Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments
A new open Minecraft benchmark for 2v2 LLM-agent competition, and a system, TactiCrafter, that beats its baselines on points and win rate.
-
SC2Arena and StarEvolve: Benchmark and Self-Improvement Framework for LLMs in Complex Decision-Making Tasks
The authors propose SC2Arena, a full-coverage StarCraft II benchmark for LLMs, and StarEvolve, a planner-executor-verifier self-improvement framework, claiming superior strategic planning.
-
Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learning
A feudal hierarchical MARL method where lower-level policies are rewarded with the upper level's advantage function, with theoretical alignment guarantees and strong benchmark results.
-
Toward Adaptable Multi-Agent Reinforcement Learning: An Assumption-Aware Review
A survey proposing adaptability as a three-part taxonomy (learning, policy, scenario-driven) for organizing and evaluating MARL under changing conditions.
-
StarDojo: Benchmarking Open-Ended Behaviors of Agentic Multimodal LLMs in Production-Living Simulations with Stardew Valley
StarDojo is a 1,000-task benchmark in Stardew Valley combining production and social activities, and the best tested MLLM (GPT-4.1) achieves only 12.7% success on its 100-task subset.
-
Artificial Generals Intelligence: Mastering Generals.io with Reinforcement Learning
A PPO agent trained with behavior cloning, self-play, and reward shaping reaches a 54.82% win rate against the previous best Generals.io bot and a reported top-25 human leaderboard position.
-
Zero-Incentive Dynamics: a look at reward sparsity through the lens of unrewarded subgoals
Unrewarded bottleneck transitions, called zero-incentive dynamics, cause state-of-the-art subgoal-based RL methods to fail, and learning quality degrades sharply with delay between subgoal completion and reward.
-
Action Dependency Graphs for Globally Optimal Coordinated Reinforcement Learning
A sparse action dependency graph derived from the coordination graph is sufficient for a locally optimal policy to be globally optimal in cooperative multi-agent RL.
-
Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean-Field Games
Exact and sample-based trust-region policy optimization provably converge to approximate Nash equilibria in finite mean-field games with Õ(1/ε^6) sample complexity.
-
AT-Drone: Benchmarking Adaptive Teaming in Multi-Drone Pursuit
AT-Drone is a benchmark for adaptive teaming in multi-drone pursuit, with four environments, seven algorithms, and real-world Crazyflie drone validation.
-
Strategy-Following Multi-Agent Deep Reinforcement Learning Considering Control Strategies Provided to Other Agents
Feeding each agent a summed map of the instructions given to the other agents makes uninstructed agents cover overlooked areas and improves object collection by roughly 8% over the baseline in the tested game.
-
Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration
Self-supervised multi-agent goal-reaching, where each agent independently learns a contrastive critic of its own observations, achieves cooperation and exploration in sparse-reward MARL tasks where standard baselines fail.
-
cMALC-D: Contextual Multi-Agent LLM-Guided Curriculum Learning with Diversity-Based Context Blending
cMALC-D uses an LLM to generate training contexts for multi-agent RL and a diversity-blending mechanism to avoid mode collapse, claiming improved generalization on traffic signal control.
-
From General Relation Patterns to Task-Specific Decision-Making in Continual Multi-Agent Coordination
RPG uses a relation capturer plus a task-conditioned hypernetwork to reduce catastrophic forgetting and enable zero-shot transfer in continual multi-agent coordination.
-
Learning Bilateral Team Formation in Cooperative Multi-Agent Reinforcement Learning
A stable-matching-based team formation method improves generalization over a greedy score-based method in cooperative multi-agent RL.
-
Light Aircraft Game : Basic Implementation and training results analysis
In the new LAG air-combat environment, HASAC scores higher than HAPPO in no-weapon coordination tasks while HAPPO scores higher in missile combat, but the results come from single runs without error bars.
-
Single-Agent Planning in a Multi-Agent System: A Unified Framework for Type-Based Planners
A layered tree-search framework unifies type-based opponent-modelling planners, and myopic safe-agents emerge as the strongest practical choice in a large multi-agent route planning benchmark.
-
Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs
Adaptively quantizing parts of an LLM's layers to FP4 can improve win rates and trading yields in latency-sensitive agent tasks, but the reported gains come from choosing the best compression level after seeing test results.
-
A Comprehensive Review of Multi-Agent Reinforcement Learning in Video Games
A survey of multi-agent reinforcement learning in video games, plus a proposed five-dimension, MDP-based classification for comparing game complexity.
-
GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective
A position paper claiming that generative-AI agents that model and predict multi-agent dynamics will replace today's reactive MARL approaches.
-
Multi-Agent Reinforcement Learning in Cybersecurity: From Fundamentals to Applications
A narrative survey of multi-agent reinforcement learning for cyber defense, reviewing game-theoretic models, cyber gyms, and applications, concluding MARL is promising but faces scalability and simulation-to-real tran...
- MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning
Discussion (0). Continue with ORCID to comment.