SURREAL-System: Fully-Integrated Stack for Distributed Deep Reinforcement Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
CPUDeep Reinforcement LearningOpenAI Gymreinforcement-learningReinforcement LearningReinforcement Learning (RL)SchedulingSimilar Papers 제목 키워드 기반
Hierarchical Stochastic Scheduling of Multi-Community Integrated Energy Systems in Uncertain Environments via Stackelberg Game
An operating entity utilizing community-integrated energy systems with a large number of small-scale distributed energy sources can easily trade with existing distribution markets. To solve the energy management and pric…
energy managementGenerative Adversarial NetworkManagementSchedulingIMSurReal Too: IMS in the Surface Realization Shared Task 2020
We introduce the IMS contribution to the Surface Realization Shared Task 2020. The new system achieves substantial improvement over the state-of-the-art system from last year, mainly due to a better token representation …
Data AugmentationOptimal Scheduling of Integrated Demand Response-Enabled Integrated Energy Systems with Uncertain Renewable Generations: A Stackelberg Game Approach
In order to balance the interests of integrated energy operator (IEO) and users, a novel Stackelberg game-based optimization framework is proposed for the optimal scheduling of integrated demand response (IDR)-enabled in…
SchedulingDistributed Stackelberg Strategies in State-based Potential Games for Autonomous Decentralized Learning Manufacturing Systems
This article describes a novel game structure for autonomously optimizing decentralized manufacturing systems with multi-objective optimization challenges, namely Distributed Stackelberg Strategies in State-Based Potenti…
Self-LearningAn Accelerated Stackelberg Game Approach for Distributed Energy Resource Aggregator participating in Energy and Reserve Markets Considering Security Check
With increasing distributed energy resoures (DERs) integration, the strategic behavior of a DER aggregator in electricity markets will significantly affect the secure operation of the distribution system. In this paper, …