Data

Tools

Indexes

Applications

Experiments

Open Source Science

rl-elevator

optimize transportation routes of elevators

https://github.com/william-dan/rl-elevator

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (9.8%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

optimize transportation routes of elevators

Basic Info
  • Host: GitHub
  • Owner: william-dan
  • License: mit
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 1.07 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created 10 months ago · Last pushed 9 months ago
Metadata Files
Readme License Citation

README.md

Elevator dispatch environment for Gym

This is a project for Reinforcement Learning Course in UniNE

Directory Structure

  • Elevators
    • envs
    • simple_elevator.py: contains the core logic of the environment
  • Solver
    • BaseSolver.py: Base class for all the solvers
    • FIFO.py: implement FIFO to solve elevator dispatch
    • LOOK.py: implement LOOK to solve elevator dispatch
  • visualization: you can use python *.py -h for all the python files in this folder to check how to use it.
    • event_plot.py: parse the render output from this environment and plot a beautiful event timeline
    • load_plot.py: parse the render output from this environment and plot a beautiful event timeline, the darker the color is, the larger load elevator has.
    • rewards_boxplot.py: You give a list of rewards to the program, it will produce a box plot to show the mean and variance of the rewards.
    • filling_plot.py: You give losses to it, it will produce a nice figure with running means and variance filling area.
    • ppo_handle.py: The PPO rewards are accumulated, I use this to recover the original rewards
  • RL_elevator.ipynb: contains the core logic of training RL models

Installation

To install your new environment, run the following commands:

{shell} pip install -r requirements.txt cd Elevators pip install -e .

Contributing

If you would like to contribute, follow these steps:

  • Fork this repository
  • Clone your fork
  • Set up pre-commit via pre-commit install

PRs may require accompanying PRs in the documentation repo.

Owner

  • Login: william-dan
  • Kind: user

Citation (CITATION.cff) 

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: elevator-gym
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: William
    family-names: Dan
    email: william.anze.dan@gmail.com
    orcid: 'https://orcid.org/0009-0004-3578-7779'
repository-code: 'https://github.com/william-dan/rl-elevator/'
abstract: an RL gym environment for elevator dispatch problem
keywords:
  - Reinforcement Learning
  - Elevator Dispatch
  - Scheduling Algorithm
license: MIT

GitHub Events

Total
  • Push event: 41
  • Create event: 2
Last Year
  • Push event: 41
  • Create event: 2

Dependencies

pyproject.toml pypi
  • gymnasium *
  • pre-commit *
  • pygame >=2.1.3
requirements.txt pypi
  • gymnasium ==1.1.1
  • numpy ==1.24.4