Timezone: »

RLlib: Abstractions for Distributed Reinforcement Learning
Eric Liang · Richard Liaw · Robert Nishihara · Philipp Moritz · Roy Fox · Ken Goldberg · Joseph Gonzalez · Michael Jordan · Ion Stoica

Fri Jul 13 12:30 AM -- 12:50 AM (PDT) @ A1

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 at http://rllib.io/.

Author Information

Eric Liang (University of California, Berkeley)
Richard Liaw (UC Berkeley)
Robert Nishihara (Unknown)
Philipp Moritz (UC Berkeley)
Roy Fox (UC Berkeley)
Ken Goldberg (UC Berkeley)
Joseph Gonzalez (UC Berkeley)
Michael Jordan (UC Berkeley)
Ion Stoica (UC Berkeley)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors