Task for spacewalk agtech engineer applicants
Description • Install • Get started • Documentation
This package contains tasks and instructions for spacewalk Agtech engineer applicants.
PCSE (Python Crop Simulation Environment) is a Python package for building crop simulation models, in particular the crop models developed in Wageningen (Netherlands). PCSE is no exception and its source code is open and licensed under the European Union Public License.
In this task, we need to solve a simple agricultural reinforcement learning problem created by modified PCSE.
Goal: MAXIMIZE RETURN!!
List of environments :
PCSE-v0
Install spwk_agtech package with :
(It is recommended to install the package in virtual environment due to dependencies)
pip install git+https://github.com/TeamSPWK/spwk-agtech-task.gitYou can use the environment like any other gym environment :
# runner
import spwk_agtech
import gym
env = gym.make("PCSE-v0") # there is just version 0 in now
rews = 0
obs = env.reset()
step = 0
while True:
step += 1
action = env.action_space.sample()
next_obs, rew, done, _ = env.step(action)
rews += rew
obs = next_obs
if done:
break🔎 If you get TIMEOUT error or any errors when getting weather data from NASA POWER server (gym.make("PCSE-v0")), Please follow the steps below.
- Execute module
make_weather_cache
python -m spwk_agtech.make_weather_cache- Try re-running the environment again.
- If it still does not work, please contact us.