onsite 0.1.3

A tool package for Onsite

Project description

Onsite is a tool package for Onsite.

Update

• Version 0.1.3

  Remove the 0 limitation for velocity.

• Version 0.1.2

  Add feature: Plot.

• Version 0.1.1

  Bug fixing.

• Version 0.1.0

  Add feature: Automatically output test results into output dir.

Installation

To get started, you'll need to have Python 3.6+ installed. Simply install onsite using pip:

pip install onsite

And you’re good to go!

Usage

The usage of this library refered to the well-known reinforcement learning library OpenAI Gym.

A simple example:

# make env from scenario (OpenScenario XML)
env,observation = onsite.env.make(scenario,output_dir)
while True:
    # planning based on observation
    action = planner.act(observation)
    # obtain new observations from env
    observation,reward,done,info = env.step(action)
    # stop simulation if done
    if done:
        break

This is just an implementation of the classic “agent-environment loop”. Each timestep, the agent chooses an action, and the environment returns an observation and a reward.