search

ai4co / rl4co

A PyTorch library for all things Reinforcement Learning (RL) for Combinatorial Optimization (CO)
https://rl4.co
MIT License
381 stars 70 forks source link

Add support for AGV in the scheduling environment. #202

Closed lshengjian closed 2 weeks ago

lshengjian commented 1 month ago

Especially in the FJSP environment with AGVs.

fedebotu commented 1 month ago

Do you have any literature/code references for such an environment?

lshengjian commented 1 month ago

Do you have any literature/code references for such an environment?

https://github.com/lshengjian/jsplab/

fedebotu commented 1 month ago

Thanks for sharing. I don't have much bandwidth at the moment, so unfortunately, I cannot implement such an environment from scratch at the moment :( Maybe @LTluttmann since he knows much more than me in scheduling, although also pretty busy doing PhD ...

This said, your code seems pretty clean! It should be more than possible to create an environment similarly to our FJSP, which is much faster than the gym implementations we checked so far. I invite you to contribute to your environment, we will be more than happy to help! :)

lshengjian commented 1 month ago

Thanks for sharing. I don't have much bandwidth at the moment, so unfortunately, I cannot implement such an environment from scratch at the moment :( Maybe @LTluttmann since he knows much more than me in scheduling, although also pretty busy doing PhD ...

This said, your code seems pretty clean! It should be more than possible to create an environment similarly to our FJSP, which is much faster than the gym implementations we checked so far. I invite you to contribute to your environment, we will be more than happy to help! :)

Thank you for your invitation. but I'm sorry I can't fully understand your FJSP environment.

fedebotu commented 1 month ago

I see, please let us know any way we could help you :)