StarCraft Multi-Agent Challenge (SMAC)
Emerging10papers using it
2021first seen
The StarCraft Multi-Agent Challenge (SMAC) is a benchmark that contains simulated environments used to evaluate the coordination, negotiation, and cooperation of autonomous artificial agents in multi-agent systems.
Papers using StarCraft Multi-Agent Challenge (SMAC) (10)
- Smacv2: An Improved Benchmark For Cooperative Multi-agent Reinforcement LearningSmac-hard: Enabling Mixed Opponent Strategy Script And Self-play On SMACAGENTIC AI IN MULTI-AGENT SYSTEMS: EXPLORING THE COORDINATION, NEGOTIATION, AND COOPERATION OF AUTONOMOUS ARTIFICIAL AGENTS IN COMPETITIVE AND COLLABORATIVE DIGITAL ECOSYSTEMSLow-rank Agent-specific Adaptation (lorasa) For Multi-agent Policy LearningCooperative Multi-Agent Planning with Adaptive Skill SynthesisEnabling Multi-Agent Transfer Reinforcement Learning via Scenario
Independent RepresentationSemi-On-Policy Training for Sample Efficient Multi-Agent Policy
GradientsMulti-Task Multi-Agent Shared Layers are Universal Cognition of
Multi-Agent CoordinationDecentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World ModelsOffline-to-Online Multi-Agent Reinforcement Learning with Offline Value Function Memory and Sequential Exploration