Rllib: Abstractions For Distributed Reinforcement Learning

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 at https://rllib.io/.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyliang2017rllib

Related papers

• Rllib Flow: Distributed Reinforcement Learning Is A Dataflow Problem (2020)0.00
• Integrating Distributed Architectures In Highly Modular RL Libraries (2020)0.00
• SRL: Scaling Distributed Reinforcement Learning To Over Ten Thousand Cores (2023)0.00
• Cleanba: A Reproducible And Efficient Distributed Reinforcement Learning Platform (2023)4.19
• Scilab-rl: A Software Framework For Efficient Reinforcement Learning And Cognitive Modeling Research (2024)0.00
• Distributed Deep Reinforcement Learning: An Overview (2020)0.00
• Acme: A Research Framework For Distributed Reinforcement Learning (2020)0.00
• Rltools: A Fast, Portable Deep Reinforcement Learning Library For Continuous Control (2023)0.00