Starcraft
129 papers with code • 0 benchmarks • 6 datasets
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 )
Benchmarks
These leaderboards are used to track progress in Starcraft
Libraries
Use these libraries to find Starcraft models and implementations
VizDoom
StarCraft II Learning Environment
Mario AI
Lani
StarData
MSC
Most implemented papers
MSC: A Dataset for Macro-Management in StarCraft II
wuhuikai/MSC
•
•
We also split MSC into training, validation and test set for the convenience of evaluation and comparison.
Explainable Reinforcement Learning Through a Causal Lens
prashanm/StarCraft-II-causal-explanations
•
•
In this paper, we use causal models to derive causal explanations of behaviour of reinforcement learning agents.
Arena: a toolkit for Multi-Agent Reinforcement Learning
We introduce Arena, a toolkit for multi-agent reinforcement learning (MARL) research.
Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control
saizhang0218/VBC
•
•
NeurIPS 2019
Multi-agent reinforcement learning (MARL) has recently received considerable attention due to its applicability to a wide range of real-world applications.
Deep Coordination Graphs
wendelinboehmer/dcg
•
•
ICML 2020
This paper introduces the deep coordination graph (DCG) for collaborative multi-agent reinforcement learning.
Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning
Multi-agent settings in the real world often involve tasks with varying types and quantities of agents and non-agent entities; however, common patterns of behavior often emerge among these agents/entities.
Learning to Play No-Press Diplomacy with Best Response Policy Iteration
deepmind/diplomacy
•
•
NeurIPS 2020
It also features a large combinatorial action space and simultaneous moves, which are challenging for RL algorithms.
RODE: Learning Roles to Decompose Multi-Agent Tasks
TonghanWang/RODE
•
•
ICLR 2021
Learning a role selector based on action effects makes role discovery much easier because it forms a bi-level learning hierarchy -- the role selector searches in a smaller role space and at a lower temporal resolution, while role policies learn in significantly reduced primitive action-observation spaces.
Multi-Agent Collaboration via Reward Attribution Decomposition
In this work, we propose Collaborative Q-learning (CollaQ) that achieves state-of-the-art performance in the StarCraft multi-agent challenge and supports ad hoc team play.
Rethinking the Implementation Matters in Cooperative Multi-Agent Reinforcement Learning
hijkzzz/pymarl2
•
•
Multi-Agent Reinforcement Learning (MARL) has seen revolutionary breakthroughs with its successful application to multi-agent cooperative tasks such as computer games and robot swarms.
