Can't find DQfD algorithm

How severe does this issue affect your experience of using Ray?

  • High: It blocks me to complete my task.

I can’t find DQfD algorithm in the latest RLlib, which is mentioned here: (
Offline RL and imitation learning/behavior cloning: You don’t have a simulator for your particular problem, but tons of historic data recorded by a legacy (maybe non-RL/ML) system? This branch of reinforcement learning is for you! RLlib’s comes with several offline RL algorithms (CQL, MARWIL, and DQfD), allowing you to either purely behavior-clone your existing system or learn how to further improve over it.)

RLlib: Industry-Grade Reinforcement Learning — Ray 1.12.1

Looks like an error in the documentation to me, it only shows up in the docs Search · DQfD · GitHub . Also the other offline RL algorithms can be found in ray/rllib/algorithms at master · ray-project/ray · GitHub , but it isnt there. There was an issue related to implementing it but nothing ever came from it.

Yeah, I hope RLlib can support DQFD as soon as possible.