SOTAVerified

SMAC

Bechmarks for Efficient Exploration of Completion of Multi-stage Tasks and Usage of Environmental Factors

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 121 papers

TitleStatusHype
Generalizable Agent Modeling for Agent Collaboration-Competition Adaptation with Multi-Retrieval and Dynamic GenerationCode0
Curriculum Learning With Counterfactual Group Relative Policy Advantage For Multi-Agent Reinforcement LearningCode1
Ensemble-MIX: Enhancing Sample Efficiency in Multi-Agent RL Using Ensemble Methods—0
Dynamic Sight Range Selection in Multi-Agent Reinforcement Learning—0
POCAII: Parameter Optimization with Conscious Allocation using Iterative Intelligence—0
JaxRobotarium: Training and Deploying Multi-Robot Policies in 10 MinutesCode1
Rainbow Delay Compensation: A Multi-Agent Reinforcement Learning Framework for Mitigating Delayed Observation—0
Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent CooperationCode0
AVA: Attentive VLM Agent for Mastering StarCraft IICode1
Low-Rank Agent-Specific Adaptation (LoRASA) for Multi-Agent Policy Learning—0
Show:102550
← PrevPage 1 of 13Next →
All datasetsSMAC MMM2SMAC 3s5z_vs_3s6zSMAC corridorSMAC 6h_vs_8zSMAC 27m_vs_30mSMAC 26m_vs_30mSMAC 3s5z_vs_4s6zSMAC 6h_vs_9zSMAC corridor_2z_vs_24zgSMAC MMM2_7m2M1M_vs_8m4M1MSMAC MMM2_7m2M1M_vs_9m3M1M

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ACEMedian Win Rate100—Unverified
2DDNMedian Win Rate97.22—Unverified
3QPLEXMedian Win Rate96.88—Unverified
4DPLEXMedian Win Rate96.88—Unverified
5DMIXMedian Win Rate95.11—Unverified
6QMIXMedian Win Rate92.44—Unverified
7VDNMedian Win Rate89.2—Unverified
8DIQLMedian Win Rate85.23—Unverified
9QMIXMedian Win Rate69—Unverified
10QMIXMedian Win Rate69—Unverified