search

Ipsedo / MARLClassification

Image classification using reinforcement learning and multi-agent system
GNU General Public License v3.0
42 stars 6 forks source link

Is the code improved based on the paper? #10

Closed tjnkyqcy closed 3 months ago

tjnkyqcy commented 3 months ago

Also, is your code based on the paper with new modifications, the code involves A2C-like strategies that don't seem to be presented in the paper, which is a bit unclear to me. I hope you can help.

Ipsedo commented 3 months ago

No the actor critic part is an enhancement. In the original paper they use policy reinforce algorithm. But results were better with actor critic algorithm.

Ipsedo commented 3 months ago

If you want the original version you can look at original-paper branch (but I don't remember if it was working). With no update on your side can I consider it as resolved and close the issue?

tjnkyqcy commented 3 months ago

Where is the ORIGINAL-PAPER branch you mentioned, sorry I couldn't find it, could you provide me with a link, thanks.

Ipsedo commented 3 months ago

https://github.com/Ipsedo/MARLClassification/tree/original-paper