Entropy-Aware Model Initialization for Effective Exploration in Deep Reinforcement Learning

Effective exploration is one of the critical factors affecting performance in deep reinforcement learning. Agents acquire data to learn the optimal policy through exploration, and if it is not guaranteed, the data quality deteriorates, which leads to performance degradation. This study investigates...

Descripción completa

Detalles Bibliográficos
Autores principales: Jang, Sooyoung, Kim, Hyung-Il
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9371101/
https://www.ncbi.nlm.nih.gov/pubmed/35957399
http://dx.doi.org/10.3390/s22155845

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9371101/
https://www.ncbi.nlm.nih.gov/pubmed/35957399
http://dx.doi.org/10.3390/s22155845

Ejemplares similares