SURREAL-System: Fully-Integrated Stack for Distributed Deep Reinforcement Learning
This provides a scalable and reproducible framework for researchers and practitioners in reinforcement learning, though it is incremental as it builds on existing algorithms with improved infrastructure.
The authors tackled the challenge of scaling deep reinforcement learning by introducing SURREAL-System, a fully-integrated stack that enables distributed algorithms like PPO and ES to scale to thousands of CPU cores and hundreds of GPUs, achieving new state-of-the-art results on OpenAI Gym and Robotics Suites tasks.
We present an overview of SURREAL-System, a reproducible, flexible, and scalable framework for distributed reinforcement learning (RL). The framework consists of a stack of four layers: Provisioner, Orchestrator, Protocol, and Algorithms. The Provisioner abstracts away the machine hardware and node pools across different cloud providers. The Orchestrator provides a unified interface for scheduling and deploying distributed algorithms by high-level description, which is capable of deploying to a wide range of hardware from a personal laptop to full-fledged cloud clusters. The Protocol provides network communication primitives optimized for RL. Finally, the SURREAL algorithms, such as Proximal Policy Optimization (PPO) and Evolution Strategies (ES), can easily scale to 1000s of CPU cores and 100s of GPUs. The learning performances of our distributed algorithms establish new state-of-the-art on OpenAI Gym and Robotics Suites tasks.