Research

RLlib: Abstractions for Distributed Reinforcement Learning

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

Download Paper

Abstract

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 as part of the open source Ray project.

Related Content

Authors: Philipp Moritz, Robert Nishihara, Stephanie Wang, Alexey Tumanov, Richard Liaw, Eric Liang, Melih Elibol, Zongheng Yang, William Paul, Michael I. Jordan, and Ion Stoica, UC Berkeley

Authors: Roy Fox, Richard Shin, Sanjay Krishnan, Ken Goldberg, Dawn Song, Ion Stoica

Authors: Firas Abuzaid, Joseph Bradley, Feynman Liang, Andrew Feng, Lee Yang, Matei Zaharia, Ameet Talwalkar

Authors: Cody Coleman, Deepak Narayanan, Daniel Kang, Tian Zhao, Jian Zhang, Luigi Nardi, Peter Bailis, Kunle Olukotun, Chris Ré, Matei Zaharia

Authors: Daniel Crankshaw, Xin Wang, Giulio Zhou, Michael J. Franklin, Joseph E. Gonzalez, Ion Stoica

Authors: Reza Bosagh Zadeh, Xiangrui Meng, Alexander Ulanov, Burak Yavuz, Li Pu, Shivaram Venkataraman, Evan Sparks, Aaron Staple, Matei Zaharia

Authors: Xiangrui Meng, Joseph Bradley, Burak Yavuz, Evan Sparks, Shivaram Venkataraman, Davies Liu, Jeremy Freeman, DB Tsai, Manish Amde, Sean Owen, Doris Xin, Reynold Xin, Michael J. Franklin, Reza Zadeh, Matei Zaharia, Ameet Talwalkar