Hi, Pete from UK

I primarily build web based applications using a variety of technology stacks (php, nodejs, .net).
Recently moved on to using Neo4j and machine learning.
Have created a few DDQN agents with Tensorflow - another awesome piece of technology.

Welcome, Pete. Glad to see you posting. I'm a big TF fan, too, as well as PyTorch. There is a lot of current innovation going on in Neo regarding deep learning.

1 Like

Thanks Brent. Yes it's great just how easily accessible ML is now. I haven't really look at PyTorch though (I need to).

Actually stuck on something relating to that, perhaps worth asking you:

Do you know how to make a DQRN agent work if you have multiple action spaces, like over 100 different actions? Or possibly two sets of different action types. At the moment I have built things that can decide on 6 actions at most and only making one decision at a time. If not no probs, thanks for the welcome.