SMAC (StarCraft II Multi-Agent Challenge) is a benchmark environment for cooperative multi-agent reinforcement learning (MARL), based on real-time strategy (RTS) game scenarios in StarCraft II. It allows researchers to test algorithms where multiple units (agents) must collaborate to win battles against built-in game AI opponents. SMAC provides a controlled testbed for studying decentralized execution and centralized training paradigms in MARL.
Features
- Focuses on decentralized multi-agent cooperation challenges
- Provides a variety of tactical combat scenarios in StarCraft II
- Supports partial observability and limited communication among agents
- Integrates with PyMARL and other MARL libraries for training
- Includes a standard benchmark for evaluating MARL algorithms
- Offers tools for measuring performance and analyzing agent coordination
Project Samples
Categories
Reinforcement Learning FrameworksLicense
MIT LicenseFollow SMAC
You Might Also Like
Gen AI apps are built with MongoDB Atlas
MongoDB Atlas is the developer-friendly database used to build, scale, and run gen AI and LLM-powered apps—without needing a separate vector database. Atlas offers built-in vector search, global availability across 115+ regions, and flexible document modeling. Start building AI apps faster, all in one place.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of SMAC!