DDPG using Flux


I need to implement DDPG (and TD3) algorithm for Julia using Flux. I saw that we have an initial implementation here:

However, the algorithm is very old and does not work with the newest version of Flux. I am wondering if anyone has already implemented a version of DDPG that works with newest Flux. If so, is it possible to provide me some tips? It seems that the Flux API changed a lot.

You could try to ask here https://github.com/JuliaReinforcementLearning/ReinforcementLearningZoo.jl/pull/16
what’s missing in the implementation

1 Like

Thanks! I was not find this pull request. This should help a lot :slight_smile: