Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Optimizing and Extending the Functionality of EXARL for Scalable Reinforcement Learning [Slides]

Technical Report ·
DOI:https://doi.org/10.2172/1812639· OSTI ID:1812639
 [1];  [2];  [3];  [4]
  1. Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Univ. of Florida, Gainesville, FL (United States)
  2. Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Univ. of New Mexico, Albuquerque, NM (United States)
  3. Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Univ. of Colorado, Colorado Springs, CO (United States)
  4. Los Alamos National Lab. (LANL), Los Alamos, NM (United States); University of Reims (France)
+ Show Author Affiliations
The main goal of the Co-Design Summer School 2021 is to provide algorithmic improvements to EXARL framework by improving performance and by adding functionalities. This presentation includes an introduction to reinforcement learning and to EXARL. The researchers expanded the capability of EXARL by including additional agents like (Asynchronized) Advantage Actor Critic (A2C/A3C) and Twin Delayed Deep Deterministic Policy Gradient (TD3). They also explored algorithmic improvements such as v-trace and Prioritized Experience Replay. They found that A2C/A3C performed best with v-trace and outperformed Deep Q-Network (DQN) on both the CartPole game and the ExaBooster scientific environment. Additionally, they found that TD3 performed as good as the existing Deep Deterministic Policy Gradient (DDPG) agent and that adding Prioritized Experience Replay to DDPG accelerated convergence.
Research Organization:
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA); USDOE Office of Science (SC)
DOE Contract Number:
89233218CNA000001
OSTI ID:
1812639
Report Number(s):
LA-UR-21-27928
Country of Publication:
United States
Language:
English

Similar Records

Federated Deep Reinforcement Learning for Decentralized VVO of BTM DERs
Conference · Mon Sep 30 20:00:00 EDT 2024 · OSTI ID:2477510
Approximating Nash Equilibrium in Day-ahead Electricity Market Bidding with Multi-agent Deep Reinforcement Learning
Journal Article · Sun Apr 18 20:00:00 EDT 2021 · Journal of Modern Power Systems and Clean Energy · OSTI ID:1782068
Deep reinforcement learning assisted co-optimization of Volt-VAR grid service in distribution networks
Journal Article · Sun Jun 11 20:00:00 EDT 2023 · Sustainable Energy, Grids and Networks · OSTI ID:2418735

Related Subjects

97 MATHEMATICS AND COMPUTING