search

prosysscience / JSSEnv

An OpenAi Gym environment for the Job Shop Scheduling problem.
MIT License
188 stars 55 forks source link

How to prevent overfitting? #15

Open smita-09 opened 2 years ago

smita-09 commented 2 years ago

Hello there,

I am working on a very similar area, that is using reinforcement learning for optimization of the semiconductor manufacturing process and your implementation is easy to follow and has been very helpful I would say. Just wanted to ask a question here, how are preventing overfitting?

I can see that you are training the model on just one instance from your instances folder and iterating it for a while, so how are making sure that the model would not overfit? I believe, it should be trained on multiple instances to make it more stable. If you are already training it on multiple instances, ignore my question but please help me by pointing me how did you achieve that in your implementation?

Cheers, Smita

ingambe commented 1 year ago

Hi,

Sorry for the late answer. This is a good question, or the first approach was just a prototype, but if you want a model that generalizes, training on multiple instances is a must, IMO. Also, the architecture of our neural network is not so good. You can get way better results with a Transformer and get a size-invariant network.