SMAC-Exp

StarCraft Multi-Agent Exploration Challenge

The StarCraft Multi-Agent Challenges+ requires agents to learn completion of multi-stage tasks and usage of environmental factors without precise reward functions. The previous challenges (SMAC) recognized as a standard benchmark of Multi-Agent Reinforcement Learning are mainly concerned with ensuring that all agents cooperatively eliminate approaching adversaries only through fine manipulation with obvious reward functions. This challenge, on the other hand, is interested in the exploration capability of MARL algorithms to efficiently learn implicit multi-stage tasks and environmental factors as well as micro-control. This study covers both offensive and defensive scenarios. In the offensive scenarios, agents must learn to first find opponents and then eliminate them. The defensive scenarios require agents to use topographic features. For example, agents need to position themselves behind protective structures to make it harder for enemies to attack.

Environment English

벤치마크

SMAC+ on Def_Armored_sequential 결과 22개

SMAC+ on Def_Outnumbered_sequential 결과 22개

SMAC+ on Def_Armored_parallel 결과 20개

SMAC+ on Def_Infantry_parallel 결과 20개

SMAC+ on Def_Outnumbered_parallel 결과 20개

SMAC+ on Off_Complicated_parallel 결과 20개

SMAC+ on Off_Distant_parallel 결과 20개

SMAC+ on Off_Hard_parallel 결과 20개

SMAC+ on Off_Near_parallel 결과 20개

SMAC+ on Off_Superhard_parallel 결과 20개

SMAC+ on Off_Superhard_sequential 결과 8개

Starcraft II on SMAC-Exp 결과 2개

Multi-agent Reinforcement Learning on SMAC-Exp 결과 1개