A hybrid approach to reinforcement learning: combining soft updating and frame stacking for stable training in Flappy Bird and CartPole

The Journal of Supercomputing 2026

View at publisher
Authors: Mohammad Hossein Jabbarzadeh, Delaram Mehralizadeh, Kimia Shirini, Sina Samadi Gharehveran
DOI: 10.1007/s11227-026-08615-1
Cited by: 1
References: 17

Fields of Study & Subjects

Biomimetic flight and propulsion mechanisms Zebrafish Biomedical Research Applications Neurobiology and Insect Physiology Research

Publication details

Journal / source
The Journal of Supercomputing
Publisher
Springer Science and Business Media LLC
Volume
82
Issue
8
Publication date
15 June 2026
Language
EN