StartCraft II Reinforcement Learning Examples

This example program was built on

Current examples

CollectMineralShards

The easiest way to get PySC2 is to use pip:

$ pip install git+https://github.com/deepmind/pysc2

Also, you have to install baselines library.

$ pip install git+https://github.com/openai/baselines

You have to purchase StarCraft II and install it. Or even the Starter Edition will work.

Follow Blizzard's documentation to get the linux version. By default, PySC2 expects the game to live in ~/StarCraftII/.

Download the ladder maps and the mini games and extract them to your StarcraftII/Maps/ directory.

$ python train_mineral_shards.py --algorithm=a2c

$ python enjoy_mineral_shards.py

$ python train_mineral_shards.py --algorithm=deepq --prioritized=True --dueling=True --timesteps=2000000 --exploration_fraction=0.2

$ python train_mineral_shards.py --algorithm=a2c --num_agents=2 --num_scripts=2 --timesteps=2000000

	Description	Default	Parameter Type
map	Gym Environment	CollectMineralShards	string
log	logging type : tensorboard, stdout	tensorboard	string
algorithm	Currently, support 2 algorithms : deepq, a2c	a2c	string
timesteps	Total training steps	2000000	int
exploration_fraction	exploration fraction	0.5	float
prioritized	Whether using prioritized replay for DQN	False	boolean
dueling	Whether using dueling network for DQN	False	boolean
lr	learning rate (if 0 set random e-5 ~ e-3)	0.0005	float
num_agents	number of agents for A2C	4	int
num_scripts	number of scripted agents for A2C	4	int
nsteps	number of steps for update policy	20	int

Project Name	Stars	Repos Using This	Packages Using This	Most Recent Commit	Total Releases	Latest Release	Open Issues	License	Language
Pysc2	7,745	20	6	a month ago	8	September 27, 2019	47	apache-2.0	Python
StarCraft II Learning Environment
Coach	2,248	1	1	6 months ago	13	October 10, 2019	90	apache-2.0	Python
Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms
Torchcraft	1,346			2 years ago			33	other	C++
Connecting Torch to StarCraft
Smac	828			2 months ago			12	mit	Python
SMAC: The StarCraft Multi-Agent Challenge
Pysc2 Examples	721			2 years ago			23	apache-2.0	Python
StarCraft II - pysc2 Deep Reinforcement Learning Examples
Awesome Game Ai	522			3 months ago				mit
Awesome Game AI materials of Multi-Agent Reinforcement Learning
Reaver	516			3 years ago	14	February 24, 2020	10	mit	Python
Reaver: Modular Deep Reinforcement Learning Framework. Focused on StarCraft II. Supports Gym, Atari, and MuJoCo.
Gym Starcraft	505			6 years ago			4		Python
StarCraft environment for OpenAI Gym, based on Facebook's TorchCraft. (In progress)
Pymarl2	425			2 months ago			3	apache-2.0	Python
Fine-tuned MARL algorithms on SMAC (100% win rates on most scenarios)
Ic3net	174			7 months ago			9	mit	Python
Code for ICLR 2019 paper: Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks