Pysc2-Examples

Visit Tool

pysc2-examples is an open-source research and education tool that provides Deep Reinforcement Learning examples for StarCraft II. It allows developers to train AI agents to play the game using various algorithms.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is pysc2-examples?

pysc2-examples offers a collection of Deep Reinforcement Learning examples specifically designed for StarCraft II. Built upon Deepmind's pysc2, OpenAI's baselines, and Blizzard's s2client-proto, it provides a robust framework for developers and researchers. The project leverages TensorFlow 1.3 and includes examples for tasks like 'CollectMineralShards' using Deep Q Networks and A2C algorithms. Users can quickly set up the environment, install necessary libraries like pysc2 and baselines, download StarCraft II maps, and then train and enjoy their AI agents. It supports various parameters for training, including algorithm choice (deepq, a2c), total timesteps, exploration fraction, and options for prioritized replay or dueling networks.

Best used for

Ideal for developers and professors who need to explore and implement Deep Reinforcement Learning algorithms within the StarCraft II environment. Especially valuable for training AI agents to perform specific in-game tasks like mineral collection or combat, and for educational purposes in AI and machine learning courses.

Common actions

train AI agents

implement reinforcement learning

experiment with deep learning

develop game AI

low-code/no-codeopen-sourceautomated workflowcollaborationworkflowsdeepfake"AI Agents"github copilotface swapping

Capabilities

Key features

Deep Q Network examples
A2C algorithm implementation
StarCraft II integration
Configurable training parameters
OpenAI baselines integration

Target Audience

developerprofessor

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What StarCraft II version is required for pysc2-examples?

pysc2-examples requires StarCraft II to be installed, with the Starter Edition being sufficient. PySC2 expects the game to be located in the default directory, typically `~/StarCraftII/` on Linux systems, or the standard installation path on Mac/Windows.

Which Deep Reinforcement Learning algorithms are supported?

The project currently supports two main algorithms: Deep Q Network (DQN) and Advantage Actor-Critic (A2C). Users can specify their preferred algorithm during training, along with various hyper-parameters to fine-tune the learning process for their AI agents.

How do I get started with training an AI agent?

To begin training, you need to install pysc2 and OpenAI baselines via pip, install StarCraft II, and download the necessary maps. Once set up, you can run Python scripts like `train_mineral_shards.py` with your chosen algorithm and parameters to start the training process.

Trending

Subcategories trending in Research & Education

Study Assistants Knowledge Management Course Creation Scientific Computing Summarization Language Learning

Trending

Also listed in

This tool also appears in

AI Agents & Automation › AI Frameworks & Infra Coding & Development › Coding Agents Coding & Development › Game Development Coding & Development › Open Source & Models

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce