Efficient Parallel Reinforcement Learning Framework Using the Reactor Model
Open Access
- 17 June 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 41-51
Abstract
Parallel Reinforcement Learning (RL) frameworks are essential for mapping RL workloads to multiple computational resources, allowing for faster generation of samples, estimation of values, and policy improvement. These computational paradigms require a seamless integration of training, serving, and simulation workloads. Existing frameworks, such as Ray, are not managing this orchestration efficiently, especially in RL tasks that demand intensive input/output and synchronization between actors on a single node. In this study, we have proposed a solution implementing the reactor model, which enforces a set of actors to have a fixed communication pattern. This allows the scheduler to eliminate work needed for synchronization, such as acquiring and releasing locks for each actor or sending and processing coordination-related messages. Our framework, Lingua Franca (LF), a coordination language based on the reactor model, also supports true parallelism in Python and provides a unified interface that allows users to automatically generate dataflow graphs for RL tasks. In comparison to Ray on a single-node multi-core compute platform, LF achieves 1.21x and 11.62x higher simulation throughput in OpenAI Gym and Atari environments, reduces the average training time of synchronized parallel Q-learning by 31.2%, and accelerates multi-agent RL inference by 5.12x.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- High-performance Deterministic Concurrency Using Lingua FrancaACM Transactions on Architecture and Code Optimization, 2023
- An Extensible, Data-Oriented Architecture for High-Performance, Many-World SimulationACM Transactions on Graphics, 2023
- A review of cooperative multi-agent deep reinforcement learningApplied Intelligence, 2022
- Toward a Lingua Franca for Deterministic Concurrent SystemsACM Transactions on Embedded Computing Systems, 2021
- Visual Navigation with Asynchronous Proximal Policy Optimization in Artificial AgentsJournal of Robotics, 2020
- DeepSpeed2020
- AuTO2018
- Modeling Timed Concurrent Systems2006
- The synchronous approach to reactive and real-time systemsProceedings of the IEEE, 1991
- Object oriented programmingACM SIGPLAN Notices, 1982