Any reason for using different models for gym and atari experiments?

kzl / decision-transformer

Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

MIT License

2.33k stars 440 forks source link

Any reason for using different models for gym and atari experiments? #47

Closed GilgameshD closed 2 years ago

GilgameshD commented 2 years ago

I am wondering if there is any reason for using different code bases and model structures for these two experiments. I am trying to use DT for other environments but not sure which version I should use. Thanks.

shahaamirbader commented 1 year ago

This seems to be a valid question, closed without response.

pwyq commented 3 months ago

I think because gym model is for continuous action spaces, while atari model is for discrete action spaces