This example program was built on
- pysc2 (Deepmind) [https://github.com/deepmind/pysc2]
- baselines (OpenAI) [https://github.com/openai/baselines]
- s2client-proto (Blizzard) [https://github.com/Blizzard/s2client-proto]
- Tensorflow 1.3 (Google) [https://github.com/tensorflow/tensorflow]
- CollectMineralShards with Deep Q Network
The easiest way to get PySC2 is to use pip:
$ pip install git+https://github.com/deepmind/pysc2Also, you have to install baselines library.
$ pip install git+https://github.com/openai/baselinesYou have to purchase StarCraft II and install it. Or even the Starter Edition will work.
http://us.battle.net/sc2/en/legacy-of-the-void/
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 |