SC2MM 0.0.3

A package for StarCraft2 Micro-Management.

SC2DC

StarCraft 2 Decentralized Control

A collection of helpful papers for SC2 decentralized control, mainly focused on:

• Micro Management
• Communication
• Planning
• Cooperation
• Coordination

Review Paper

• Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms
• A Survey of Real-Time Strategy Game AI Research and Competition in StarCraft

Research Paper

• Mutiagent Bidirectionally-Coordinated Nets Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games
• StarCraft II Build Order Optimization using Deep Reinforcement Learning and Monte-Carlo Tree Search
• QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
• Efficient Communication in Multi-AgentReinforcement Learning via Variance Based Control
• Deep Multi-Agent Reinforcement Learning for Decentralised Continuous Cooperative Control
• Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks
• Deep Coordination Graphs
• The StarCraft Multi-Agent Challenge
• An Analysis of Model-Based Heuristic Search Techniques for StarCraft Combat Scenarios
• Multi-scale Bayesian modeling for RTS games: an application to StarCraft AI
• Learning to Select Actions in Starcraft with Genetic Algorithms
• Neuroevolution for RTS Micro
• Real-time challenge balance in an RTS game using rtNEAT
• Neuroevolution Based Multi-Agent System with Ontology Based Template Creation for Micromanagement in Real-Time Strategy Games
• Potential-Field-Based Unit Behavior Optimization for Balancing in StarCraft II
• Comparing Three Approaches to Micro in RTS Games
• Attentive Relational State Representation in Decentralized Multiagent Reinforcement Learning
• Spellcaster Control Agent in StarCraft II Using Deep Reinforcement Learning
• Learning to Select Actions in StarCraft with Genetic Algorithms
• Comparing Three Approaches to Micro in RTS Games
• Neuroevolution for RTS Micro
• Neuroevolution Based Multi-Agent System with Ontology Based Template Creation for Micromanagement in Real-Time Strategy Games
• Evolving Neural Networks through Augmenting Topologies

Thesis

• Heuristic Search Techniques for Real-Time Strategy Games

Environment / Simulation / API

• pysc2
• SparCraft
• Brood War API
• SMAC

Maps

• You can find a list of maps here

Run

To get started:

python -m scdc.agents.scripted..agent_demo

Acknowledgement

• The coding is based on SMAC. Refer to the repo for details and license.