KAN-Based On-Policy PPO Method for Continuous Reinforcement Learning

Communications in computer and information science 2026

View at publisher
Authors: Ali Bayeh, Malek Mouhoub, Samira Sadaoui
DOI: 10.1007/978-3-032-13589-6_1
Cited by: 1
References: 9

Fields of Study & Subjects

Reinforcement Learning in Robotics Adaptive Dynamic Programming Control Advanced Bandit Algorithms Research

Publication details

Journal / source
Communications in computer and information science
Publisher
Springer Nature Switzerland
Pages
3–15
Publication date
1 January 2026
Language
EN