No project description provided
Project description
Gym-MicroRTS
This repo contains the source code for the gym wrapper of MicroRTS authored by Santiago Ontañón.
Get Started
$ pip install gym_microrts
And run either the hello_world.py
referenced above or the following file
import gym
import gym_microrts
env = gym.make("MicrortsMining-v1")
env.reset()
for _ in range(10000):
env.render()
env.step(env.action_space.sample())
env.close()
Developer Guide
Clone the repo
# install gym-microrts
$ git clone --recursive https://github.com/vwxyzjn/gym-microrts.git && \
cd gym-microrts && \
pip install -e .
# build microrts
$ cd gym_microrts/microrts && bash build.sh && cd ..& cd ..
$ python hello_world.py
Papers written using gym-microrts
- Comparing Observation and Action Representations for Deep Reinforcement Learning in MicroRTS (https://arxiv.org/abs/1910.12134)
- Logged experiments https://app.wandb.ai/costa-huang/MicrortsRL
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
gym_microrts-0.1.5.tar.gz
(36.4 MB
view hashes)