Distributed Policy Optimizers for Scalable and Reproducible Deep RL

Eric Liang blog, Deep Learning, Distributed Systems, Open Source, Ray, Reinforcement Learning 0 Comments

In this blog post we introduce Ray RLlib, an RL execution toolkit built on the Ray distributed execution framework. RLlib implements a collection of distributed policy optimizers that make it easy to use a variety of training strategies with existing reinforcement learning algorithms written in frameworks such as PyTorch, TensorFlow, and Theano. This enables complex architectures for RL training (e.g., Ape-X, IMPALA), to be implemented once and reused many times across different RL algorithms and libraries. We discuss in more detail the design and performance of policy optimizers in the RLlib paper. What’s next for RLlib In the near term we plan to continue building out RLlib’s set of policy optimizers and algorithms. Our aim is for RLlib to serve …

RLlib: Abstractions for Distributed Reinforcement Learning

Eric Liang

Reinforcement learning (RL) algorithms involve the deep nesting of highly irregular computation patterns, each of which typically exhibits opportunities for distributed computation. We argue for distributing RL components in a composable way by adapting algorithms for top-down hierarchical control, thereby encapsulating parallelism and resource requirements within short-running compute tasks. We demonstrate the benefits of this principle through RLlib: a library that provides scalable software primitives for RL. These primitives enable a broad range of algorithms to be implemented with high performance, scalability, and substantial code reuse. RLlib is available at https://github.com/ray-project/ray.

Authors: Eric Liang, Richard Liaw, Robert Nishihara, Philipp Moritz, Roy Fox, Kenneth Goldberg, Joseph Gonzalez, Michael Jordan, Ion Stoica