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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 76–100 of 175 papers

Title	Date	Tasks	Status	Score
MSC: A Dataset for Macro-Management in StarCraft II	Oct 9, 2017	ManagementReal-Time Strategy Games	CodeCode Available	5
Multi-Agent Common Knowledge Reinforcement Learning	Oct 27, 2018	Multi-agent Reinforcement Learningreinforcement-learning	CodeCode Available	5
Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning	Dec 20, 2024	DiversityMulti-agent Reinforcement Learning	CodeCode Available	5
On the Limitations of Elo: Real-World Games, are Transitive, not Additive	Jun 21, 2022	StarcraftStarcraft II	CodeCode Available	5
PAC: Assisted Value Factorisation with Counterfactual Predictions in Multi-Agent Reinforcement Learning	Jun 22, 2022	counterfactualMulti-agent Reinforcement Learning	CodeCode Available	5
PMAT: Optimizing Action Generation Order in Multi-Agent Reinforcement Learning	Feb 23, 2025	Action GenerationDecision Making	CodeCode Available	5
Relational Deep Reinforcement Learning	Jun 5, 2018	Deep Reinforcement Learningreinforcement-learning	CodeCode Available	5
Self-Motivated Multi-Agent Exploration	Jan 5, 2023	Multi-agent Reinforcement LearningSMAC	CodeCode Available	5
StarCraft II: A New Challenge for Reinforcement Learning	Aug 16, 2017	Deep Reinforcement LearningReal-Time Strategy Games	CodeCode Available	5
Tackling Uncertainties in Multi-Agent Reinforcement Learning through Integration of Agent Termination Dynamics	Jan 21, 2025	Distributional Reinforcement LearningMulti-agent Reinforcement Learning	CodeCode Available	5
The Natural Language of Actions	Feb 4, 2019	reinforcement-learningReinforcement Learning	CodeCode Available	5
TStarBots: Defeating the Cheating Level Builtin AI in StarCraft II in the Full Game	Sep 19, 2018	AI AgentDecision Making	CodeCode Available	5
Cooperative Multi-Agent Reinforcement Learning with Hypergraph Convolution	Dec 9, 2021	Multi-agent Reinforcement Learningreinforcement-learning	CodeCode Available	5
Value Functions Factorization with Latent State Information Sharing in Decentralized Multi-Agent Policy Gradients	Jan 4, 2022	StarcraftStarcraft II	CodeCode Available	5
Variational Saccading: Efficient Inference for Large Resolution Images	Dec 8, 2018	General Classificationimage-classification	CodeCode Available	5
MARNET: Backdoor Attacks against Value-Decomposition Multi-Agent Reinforcement Learning	Sep 29, 2021	Backdoor AttackDeep Reinforcement Learning	—Unverified	0
Forecasting Evolution of Clusters in Game Agents with Hebbian Learning	Aug 19, 2022	ClusteringMulti-agent Reinforcement Learning	—Unverified	0
Fidelity-Induced Interpretable Policy Extraction for Reinforcement Learning	Sep 12, 2023	Decision MakingDeep Reinforcement Learning	—Unverified	0
Minimax Exploiter: A Data Efficient Approach for Competitive Self-Play	Nov 28, 2023	Atari GamesDiversity	—Unverified	0
A Limited-Capacity Minimax Theorem for Non-Convex Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural Nets	Feb 14, 2020	StarcraftStarcraft II	—Unverified	0
Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization	Oct 15, 2023	Multi-agent Reinforcement LearningOff-policy evaluation	—Unverified	0
MIXRTs: Toward Interpretable Multi-Agent Reinforcement Learning via Mixing Recurrent Soft Decision Trees	Sep 15, 2022	Multi-agent Reinforcement Learningreinforcement-learning	—Unverified	0
Modular Architecture for StarCraft II with Deep Reinforcement Learning	Nov 8, 2018	Deep Reinforcement Learningreinforcement-learning	—Unverified	0
Towards a Deep Reinforcement Learning Approach for Tower Line Wars	Dec 17, 2017	Deep Reinforcement LearningQ-Learning	—Unverified	0
Towards Understanding Cooperative Multi-Agent Q-Learning with Value Factorization	May 31, 2020	counterfactualMulti-agent Reinforcement Learning	—Unverified	0

Show:10 25 50

← PrevPage 4 of 7Next →

No leaderboard results yet.