search

twni2016 / pomdp-baselines

Simple (but often Strong) Baselines for POMDPs in PyTorch, ICML 2022
https://sites.google.com/view/pomdp-baselines
MIT License
307 stars 42 forks source link

Same image encoder for RNN and Actor/Critic shortcut? #15

Closed RobertMcCarthy97 closed 1 year ago

RobertMcCarthy97 commented 1 year ago

According to Figure 7 of the paper, separate modules are used to create observation embeddings for the RNN and shortcut observations for the actor/critic MLP head respectively.

However, in the code it appears that the same image encoder is used to create image embeddings for the RNN and MLP (e.g. the same self.image_encoder is used in get_obs_embedding()and get_shortcut_obs_embedding() here).

Was there any reason for this design choice?

twni2016 commented 1 year ago

Hi, this is a minor detail. In addition, I think using shortcuts or not won't make a difference to performance. Feel free to make your own design.