SOTAVerified|Agents Browse Leaderboard About

Starcraft

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

( Image credit: Macro Action Selection with Deep Reinforcement Learning in StarCraft )

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 281–290 of 311 papers

Title	Date	Tasks	Status	Hype
PPS-QMIX: Periodically Parameter Sharing for Accelerating Convergence of Multi-Agent Reinforcement Learning	Mar 5, 2024	Federated LearningMulti-agent Reinforcement Learning	CodeCode Available	0
StarCraft Micromanagement with Reinforcement Learning and Curriculum Transfer Learning	Apr 3, 2018	Real-Time Strategy Gamesreinforcement-learning	CodeCode Available	0
Neural-encoding Human Experts' Domain Knowledge to Warm Start Reinforcement Learning	Feb 15, 2019	Deep Reinforcement LearningImitation Learning	CodeCode Available	0
MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization	Feb 21, 2023	Decision MakingMulti-agent Reinforcement Learning	CodeCode Available	0
STARDATA: A StarCraft AI Research Dataset	Aug 7, 2017	DiversityImitation Learning	CodeCode Available	0
Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks	Dec 23, 2018	Starcraft	CodeCode Available	0
Learning Explicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning via Polarization Policy Gradient	Oct 10, 2022	Multi-agent Reinforcement Learningreinforcement-learning	CodeCode Available	0
Value Functions Factorization with Latent State Information Sharing in Decentralized Multi-Agent Policy Gradients	Jan 4, 2022	StarcraftStarcraft II	CodeCode Available	0
Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learning	Mar 28, 2024	Graph LearningMulti-agent Reinforcement Learning	CodeCode Available	0
Strangeness-driven Exploration in Multi-Agent Reinforcement Learning	Dec 27, 2022	Efficient ExplorationMulti-agent Reinforcement Learning	CodeCode Available	0

Show:10 25 50

← PrevPage 29 of 32Next →

No leaderboard results yet.