search

Coac / CommNet-BiCnet

CommNet and BiCnet implementation in tensorflow
54 stars 18 forks source link

variable sharability among critic and actor #2

Open PeiYingjun opened 6 years ago

PeiYingjun commented 6 years ago

Thanks for reply, I have been busy at another project last few days, recently I get spare time. I have noticed that at comm_net, the variables of communication part(maybe along with encoder part) are not shared between critic and actor, I don't know whether it should be like these way in regular algorithms trained by DDPG like comm_net?

Coac commented 6 years ago

Well, I am not sure, but it seems that lots of actor-critic architecture shared the core layers and just use different heads. The two parts need to understand the environment, so sharing the features of the world might be faster for training. If you have time to try it, do not hesitate to make a PR

PeiYingjun commented 6 years ago

Exactly, I'm trying to rewrite the code