Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

playing-games

SMAC

3260 papers • 126 benchmarks • 313 datasets

The StarCraft Multi-Agent Challenge (SMAC) is a benchmark that provides elements of partial observability, challenging dynamics, and high-dimensional observation spaces. SMAC is built using the StarCraft II game engine, creating a testbed for research in cooperative MARL where each game unit is an independent RL agent.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in smac-1

Trend

Dataset

Best Model

Actions

SMAC 6h_vs_8z

SMAC 6h_vs_8z

SMAC MMM2

SMAC MMM2

SMAC corridor

SMAC corridor

Libraries

i

Use these libraries to find smac-1 models and implementations

2 papers 1,713

Datasets

SMAC

Subtasks

Most implemented papers

The StarCraft Multi-Agent Challenge

Tabish Rashid, Mikayel Samvelyan, C. S. D. Witt, Gregory Farquhar, Jakob N. Foerster, Shimon Whiteson, Philip H. S. Torr, Nantas Nardelli, Tim G. J. Rudner, Chia-Man Hung•Sun Feb 10 2019

The StarCraft Multi-Agent Challenge (SMAC), based on the popular real-time strategy game StarCraft II, is proposed as a benchmark problem and an open-source deep multi-agent RL learning framework including state-of-the-art algorithms is opened.

1131

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

SMAC 3s5z_vs_3s6z

SMAC 3s5z_vs_3s6z

SMAC 27m_vs_30m

SMAC 27m_vs_30m

SMAC 6h_vs_9z

SMAC 6h_vs_9z

SMAC 3s5z_vs_4s6z

SMAC 3s5z_vs_4s6z

SMAC MMM2_7m2M1M_vs_8m4M1M

SMAC MMM2_7m2M1M_vs_8m4M1M

SMAC MMM2_7m2M1M_vs_9m3M1M

SMAC MMM2_7m2M1M_vs_9m3M1M

SMAC 26m_vs_30m

SMAC 26m_vs_30m

SMAC corridor_2z_vs_24zg

SMAC corridor_2z_vs_24zg

Denys88/rl_games

2 papers 704

0

Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?

C. S. D. Witt, Shimon Whiteson, Philip H. S. Torr, Viktor Makoviychuk, Tarun Gupta, Denys Makoviichuk, Mingfei Sun•Tue Nov 17 2020

It is demonstrated that Independent PPO (IPPO), a form of independent learning in which each agent simply estimates its local value function, can perform just as well as or better than state-of-the-art joint learning approaches on popular multi-agent benchmark suite SMAC with little hyperparameter tuning.

485 0

mlrMBO: A Modular Framework for Model-Based Optimization of Expensive Black-Box Functions

B. Bischl, Michel Lang, Jakob Richter, Janek Thomas, Jakob Bossek, Daniel Horn•Wed Mar 08 2017

We present mlrMBO, a flexible and comprehensive R toolbox for model-based optimization (MBO), also known as Bayesian optimization, which addresses the problem of expensive black-box optimization by approximating the given objective function through a surrogate regression model. It is designed for both single- and multi-objective optimization with mixed continuous, categorical and conditional parameters. Additional features include multi-point batch proposal, parallelization, visualization, logging and error-handling. mlrMBO is implemented in a modular fashion, such that single components can be easily replaced or adapted by the user for specific use cases, e.g., any regression learner from the mlr toolbox for machine learning can be used, and infill criteria and infill optimizers are easily exchangeable. We empirically demonstrate that mlrMBO provides state-of-the-art performance by comparing it on different benchmark scenarios against a wide range of other optimizers, including DiceOptim, rBayesianOptimization, SPOT, SMAC, Spearmint, and Hyperopt.

176 0

MAVEN: Multi-Agent Variational Exploration

Tabish Rashid, Mikayel Samvelyan, Shimon Whiteson, Anuj Mahajan•Tue Oct 15 2019

This paper analyses value-based methods that are known to have superior performance in complex environments and proposes a novel approach called MAVEN that hybridises value and policy-based methods by introducing a latent space for hierarchical control.

408 0

FACMAC: Factored Multi-Agent Centralised Policy Gradients

Tabish Rashid, C. S. D. Witt, Shimon Whiteson, Philip H. S. Torr, Bei Peng, Pierre-Alexandre Kamienny, Wendelin Bohmer•Fri Mar 13 2020

FACMAC is a new method for cooperative multi-agent reinforcement learning in both discrete and continuous action spaces that uses a centralised but factored critic, which combines per-agent utilities into the joint action-value function via a non-linear monotonic function.

330 0

Rethinking the Implementation Tricks and Monotonicity Constraint in Cooperative Multi-Agent Reinforcement Learning

Jian Hu, Siyang Jiang, Seth Austin Harding, Haibin Wu, Shihua Liao•Fri Feb 05 2021

The experiment results show that QMIX with normalized optimizations outperforms other works in SMAC, and beyond the common wisdom from these works, the monotonicity constraint can improve sample efficiency inSMAC and DEPP.

106 0

Efficient Hyperparameter Optimization for Deep Learning Algorithms Using Deterministic RBF Surrogates

Jiashi Feng, Ilija Ilievski, Taimoor Akhtar, C. Shoemaker•Thu Jun 30 2016

A new deterministic and efficient hyperparameter optimization method that employs radial basis functions as error surrogates, called HORD, which significantly outperforms the well-established Bayesian optimization methods such as GP, SMAC, and TPE.

161 0

Efficient Evolutionary Methods for Game Agent Optimisation: Model-Based is Best

Diego Perez Liebana, S. Lucas, Jialin Liu, Ivan Bravi, Raluca D. Gaina, John R. Woodward, Vanessa Volz•Wed Jan 02 2019

A simple and fast variant of Planet Wars used as a test-bed for statistical planning based Game AI agents, and for noisy hyper-parameter optimisation, using the recently developed N-Tuple Bandit Evolutionary Algorithm.

24 0

On the Performance of Differential Evolution for Hyperparameter Tuning

Shahd Safarani, Mischa Schmidt, J. Gastinger, Tobias Jacobs, S. Nicolas, A. Schülke•Sun Apr 14 2019

The results indicate that Differential Evolution outperforms SMAC for most datasets when tuning a given machine learning algorithm - particularly when breaking ties in a first-to-report fashion.

24 0

SMIX(λ): Enhancing Centralized Value Functions for Cooperative Multiagent Reinforcement Learning

Xinghu Yao, Chao Wen, Yuhui Wang, Xiaoyang Tan•Sun Nov 10 2019

This article proposes an approach, named SMIX, that uses an OFF-policy training to achieve this by avoiding the greedy assumption commonly made in CVF learning and can be used as a general tool to improve the overall performance of other centralized training with decentralized execution (CTDE)-type algorithms by enhancing their CVFs.

55 0

Adding a benchmark result helps the community track progress.

SMAC | State-of-the-Art