RLlib: Abstractions for Distributed Reinforcement Learning
This addresses the problem of efficient and composable distributed computation for reinforcement learning practitioners, though it is incremental as it builds on existing hierarchical control concepts.
The paper tackles the challenge of distributed reinforcement learning by introducing RLlib, a library that provides scalable software primitives, enabling high performance, scalability, and code reuse for a broad range of algorithms.
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://rllib.io/.