SOTAVerified

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

Showing 76100 of 311 papers

TitleStatusHype
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-LearningCode1
C-COMA: A CONTINUAL REINFORCEMENT LEARNING MODEL FOR DYNAMIC MULTIAGENT ENVIRONMENTSCode1
Rethinking the Implementation Matters in Cooperative Multi-Agent Reinforcement LearningCode1
PushWorld: A benchmark for manipulation planning with tools and movable obstaclesCode1
Real World Games Look Like Spinning TopsCode1
Celebrating Diversity in Shared Multi-Agent Reinforcement LearningCode1
SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-LearningCode1
Settling the Variance of Multi-Agent Policy GradientsCode1
An Introduction of mini-AlphaStarCode1
TStarBot-X: An Open-Sourced and Comprehensive Study for Efficient League Training in StarCraft II Full GameCode1
PAC: Assisted Value Factorisation with Counterfactual Predictions in Multi-Agent Reinforcement LearningCode0
Action Semantics Network: Considering the Effects of Actions in Multiagent SystemsCode0
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement LearningCode0
On the Limitations of Elo: Real-World Games, are Transitive, not AdditiveCode0
PMAT: Optimizing Action Generation Order in Multi-Agent Reinforcement LearningCode0
Off-Policy Correction For Multi-Agent Reinforcement LearningCode0
PPS-QMIX: Periodically Parameter Sharing for Accelerating Convergence of Multi-Agent Reinforcement LearningCode0
A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement LearningCode0
Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement LearningCode0
Explainable Reinforcement Learning Through a Causal LensCode0
Multi-Agent Common Knowledge Reinforcement LearningCode0
MSC: A Dataset for Macro-Management in StarCraft IICode0
Arena: a toolkit for Multi-Agent Reinforcement LearningCode0
MazeBase: A Sandbox for Learning from GamesCode0
Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat GamesCode0
Show:102550
← PrevPage 4 of 13Next →

No leaderboard results yet.