Saved in:
Bibliographic Details
Main Authors: Choe, Jean Seong Bjorn, Choi, Bumkyu, Kim, Jong-kook
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.07516
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909607704657920
author Choe, Jean Seong Bjorn
Choi, Bumkyu
Kim, Jong-kook
author_facet Choe, Jean Seong Bjorn
Choi, Bumkyu
Kim, Jong-kook
contents This report presents our reinforcement learning-based approach for the swing-up and stabilisation tasks of the acrobot and pendubot, tailored specifcially to the updated guidelines of the 3rd AI Olympics at ICRA 2025. Building upon our previously developed Average-Reward Entropy Advantage Policy Optimization (AR-EAPO) algorithm, we refined our solution to effectively address the new competition scenarios and evaluation metrics. Extensive simulations validate that our controller robustly manages these revised tasks, demonstrating adaptability and effectiveness within the updated framework.
format Preprint
id arxiv_https___arxiv_org_abs_2505_07516
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Average-Reward Maximum Entropy Reinforcement Learning for Global Policy in Double Pendulum Tasks
Choe, Jean Seong Bjorn
Choi, Bumkyu
Kim, Jong-kook
Robotics
This report presents our reinforcement learning-based approach for the swing-up and stabilisation tasks of the acrobot and pendubot, tailored specifcially to the updated guidelines of the 3rd AI Olympics at ICRA 2025. Building upon our previously developed Average-Reward Entropy Advantage Policy Optimization (AR-EAPO) algorithm, we refined our solution to effectively address the new competition scenarios and evaluation metrics. Extensive simulations validate that our controller robustly manages these revised tasks, demonstrating adaptability and effectiveness within the updated framework.
title Average-Reward Maximum Entropy Reinforcement Learning for Global Policy in Double Pendulum Tasks
topic Robotics
url https://arxiv.org/abs/2505.07516