EXARL

Easily eXtendable Architecture for Reinforcement Learning (EXARL) is scalable software framework for reinforcement learning agents, environments, and workflows used for the Design and Control applications.

Contents:

• Software Requirements
• Directory Organization
• Installation
  • Manual Installation
• CANDLE Integration
• Running EXARL using MPI
• EXARL Environments
  • Creating Custom Environments
  • Using Environment Written in a Lower Level Language
• EXARL Agents
  • Creating custom agents
• EXARL Workflows
  • Creating Custom Workflows
• Base Classes
• EXARL Utils
  • Debugging, Timing, and Profiling
• EXARL Unit Tests
  • Unit Testing for ExaRL
  • Unit Test Cases for DQN agent
  • Run
  • Integration with Travis CI
• ECP Annual Meeting 21 - EXARL Tutorial
  • Getting Training Account on NERSC
  • Installation on NERSC Cori

Cite this software

@misc{EXARL,
author = {Vinay Ramakrishnaiah, Malachi Schram, Jamal Mohd-Yusof, Sayan Ghosh, Yunzhi Huang, Ai Kagawa, Christine Sweeney, Shinjae Yoo},
title = {Easily eXtendable Architecture for Reinforcement Learning (EXARL)},
year = {2020},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/exalearn/ExaRL}},
}

Contacts

If you have any questions or concerns regarding EXARL, please contact Vinay Ramakrishnaiah (vinayr@lanl.gov) and/or Malachi Schram (Malachi.Schram@pnnl.gov).