Combining Learning Agents with Behavior Tree ?

Combining Behavior Trees with reinforcement learning is an interesting idea which can enable game AI to deal with the game complexities while not being repetitive and dull. I did toy with Unreal’s BT to enable RL few years ago (and unification seemed plausible if I remember correctly).

However I don’t think current state of learning agents incorporates BT functionality. Although there is a white paper for this very purpose, not Unreal based yet, but for a 2d game called Raven.

  1. A Reinforcement Learning Behavior Tree Framework for Game AI

I hope there are other papers too on this very idea.