`

Timezone: »

 
Poster
RLlib Flow: Distributed Reinforcement Learning is a Dataflow Problem
Eric Liang · Zhanghao Wu · Michael Luo · Sven Mika · Joseph Gonzalez · Ion Stoica

Thu Dec 09 04:30 PM -- 06:00 PM (PST) @ Virtual #None
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 RLlib Flow, a hybrid actor-dataflow programming model for distributed RL, and validate its practicality by porting the full suite of algorithms in RLlib, a widely adopted distributed RL library. Concretely, RLlib Flow provides 2-9$\times$ code savings in real production code and enables the composition of multi-agent algorithms not possible by end users before. The open-source code is available as part of RLlib at https://github.com/ray-project/ray/tree/master/rllib.

Author Information

Eric Liang (University of California Berkeley)
Zhanghao Wu (University of California Berkeley)
Michael Luo (University of California Berkeley)
Sven Mika
Joseph Gonzalez (UC Berkeley)
Ion Stoica (University of California-Berkeley)

More from the Same Authors