SOTAVerified

Starcraft II

Starcraft II is a RTS game; the task is to train an agent to play the game.

( Image credit: The StarCraft Multi-Agent Challenge )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 175 papers

TitleStatusHype
SwarmBrain: Embodied agent for real-time strategy game StarCraft II via large language modelsCode1
BET: Explaining Deep Reinforcement Learning through The Error-Prone Decisions—0
StarCraftImage: A Dataset For Prototyping Spatial Reasoning Methods For Multi-Agent Environments—0
Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization ApproachCode2
DCIR: Dynamic Consistency Intrinsic Reward for Multi-Agent Reinforcement Learning—0
CODEX: A Cluster-Based Method for Explainable Reinforcement LearningCode0
Minimax Exploiter: A Data Efficient Approach for Competitive Self-Play—0
JaxMARL: Multi-Agent RL Environments and Algorithms in JAXCode2
Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization—0
Fidelity-Induced Interpretable Policy Extraction for Reinforcement Learning—0
Leveraging World Model Disentanglement in Value-Based Multi-Agent Reinforcement Learning—0
FoX: Formation-aware exploration in multi-agent reinforcement learningCode1
Never Explore Repeatedly in Multi-Agent Reinforcement Learning—0
AlphaStar Unplugged: Large-Scale Offline Reinforcement LearningCode2
Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value RegularizationCode1
Semantic HELM: A Human-Readable Memory for Reinforcement LearningCode1
Offline Multi-Agent Reinforcement Learning with Coupled Value Factorization—0
EXPODE: EXploiting POlicy Discrepancy for Efficient Exploration in Multi-agent Reinforcement LearningCode0
Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?Code1
Boosting Value Decomposition via Unit-Wise Attentive State Representation for Cooperative Multi-Agent Reinforcement Learning—0
SMAClite: A Lightweight Environment for Multi-Agent Reinforcement LearningCode1
Effective and Stable Role-Based Multi-Agent Collaboration by Structural Information PrinciplesCode1
SVDE: Scalable Value-Decomposition Exploration for Cooperative Multi-Agent Reinforcement Learning—0
AIIR-MIX: Multi-Agent Reinforcement Learning Meets Attention Individual Intrinsic Reward Mixing Network—0
Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority InfluenceCode1
Show:102550
← PrevPage 2 of 7Next →

No leaderboard results yet.