Average-Reward Maximum Entropy Reinforcement Learning for Underactuated Double Pendulum Tasks

Autor:	Choe, Jean Seong Bjorn, Choi, Bumkyu, Kim, Jong-kook
Rok vydání:	2024
Předmět:	Computer Science - Robotics Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	This report presents a solution for the swing-up and stabilisation tasks of the acrobot and the pendubot, developed for the AI Olympics competition at IROS 2024. Our approach employs the Average-Reward Entropy Advantage Policy Optimization (AR-EAPO), a model-free reinforcement learning (RL) algorithm that combines average-reward RL and maximum entropy RL. Results demonstrate that our controller achieves improved performance and robustness scores compared to established baseline methods in both the acrobot and pendubot scenarios, without the need for a heavily engineered reward function or system model. The current results are applicable exclusively to the simulation stage setup.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2409.08938 Zobrazit plný text záznamu View this record from Arxiv