Coder Social home page Coder Social logo

frenkowski / scimai-gym Goto Github PK

View Code? Open in Web Editor NEW
68.0 4.0 20.0 185.96 MB

A Python library for addressing the Supply Chain Inventory Management problem through Deep Reinforcement Learning algorithms.

Home Page: https://www.frenkowski.it

License: MIT License

Jupyter Notebook 100.00%
artificial-intelligence deep-learning inventory-control reinforcement-learning supply-chain-management

scimai-gym's People

Contributors

frenkowski avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar

scimai-gym's Issues

Code question

Hi there,
I'm not sure if this is a right place to ask the question - if yes, please forgive me.

First of all, congratulations on a great job!
My doubts, however, concern the calculations that take place in the SupplyChainEnvironment class, in the step method. I found there a line describing the equation:

next_state.factory_stocks = np.minimum(
np.subtract(np.add(state.factory_stocks,
action.production_level),
np.sum(action.shipped_stocks, axis=0)
),
self.storage_capacities[0]
)

If I understand correctly, the result of next_state.factory_stocks must not exceed the storage capacity. On the other hand, this is calculated after the action has already taken place, so it will not always be in accordance with the actual situation, because it might happen that after calculating next_state.factory_stocks we will receive value greater than we are able to stock (in this code excess poroducts evaporate). How can I understand this procedure in the context of the learning process?

Thank you in advance for response !

Ray Version - Complexities

Hello

Have been able to replicate the exact scenarios that you have mentioned in the paper. One question that I would like to ask, is were you able to try the same model with more complexities involved such as n number of warehouses/products? The reason I ask is the Ray version fails as more complexities get into the picture. Have you tried that? Wanted your opinions on it. Thank you so much!

Regarding the environment issue with 'ECML-PKDD_SCIMAI-Gym.ipynb'

Hello, when I was reproducing the code in 'ECML-PKDD_SCIMAI-Gym.ipynb', after installing the necessary dependencies like ray 1.5.2, I encountered the following error during the reinforcement learning training step:“ERROR services.py:1254 -- Failed to start the dashboard: Failed to read dashbord log: [Errno 2] No such file or directory: 'C:\Users\LENOVO\AppData\Local\Temp\ray\session_2024-02-20_14-41-15_370942_18176\logs\dashboard.log'”.
I suspect that this issue is caused by conflicts between various packages. Could you please provide the 'requirements.txt' file? Thank you. Wishing you all the best.

The result files do not open

Hello!

Great paper!
Am trying to replicate the paper with the codes that you have provided. To compare the results I am trying to look at your Results zip file and none of them open correctly. It says ' The file is invalid'. Can you please check on this? Thank you!

Query Regarding Oracle Section in Your Project

I hope this message finds you well. I am currently a student exploring your project on GitHub, and I've been encountering some difficulties understanding the Oracle section. Despite my efforts, I haven't been able to locate any Oracle-related components within the project.

I am keen on delving deeper into the Oracle section of your project, as I believe it would greatly benefit my learning and understanding of the project as a whole. Could you kindly direct me to where I can find the Oracle section within the project, or perhaps offer some guidance on how to further explore this aspect?

I truly appreciate your time and assistance. Your project has captured my interest, and I am eager to gain more insights into it.

Thank you very much.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.