Log In Sign Up

Distributed Reinforcement Learning is a Dataflow Problem

by   Eric Liang, et al.

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.


page 6

page 9


RLgraph: Flexible Computation Graphs for Deep Reinforcement Learning

Reinforcement learning (RL) tasks are challenging to implement, execute ...

Acme: A Research Framework for Distributed Reinforcement Learning

Deep reinforcement learning has led to many recent-and groundbreaking-ad...

A Distributed Reinforcement Learning Solution With Knowledge Transfer Capability for A Bike Rebalancing Problem

Rebalancing is a critical service bottleneck for many transportation ser...

Escape Room: A Configurable Testbed for Hierarchical Reinforcement Learning

Recent successes in Reinforcement Learning have encouraged a fast-growin...