Researchers and practitioners in the field of reinforcement learning (RL) frequently leverage parallel computation, which has led to a plethora of new algorithms and systems in the last few years. In this paper, we re-examine the challenges posed by distributed RL and try to view it through the lens of an old idea: distributed dataflow. We show that viewing RL as a dataflow problem leads to highly composable and performant implementations. We propose AnonFlow, a hybrid actor-dataflow programming model for distributed RL, and validate its practicality by porting the full suite of algorithms in AnonLib, a widely-adopted distributed RL library.

Distributed Reinforcement Learning is a Dataflow Problem