On the Reduction of Variance and Overestimation of Deep Q-Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2019
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929312543801344 |
|---|---|
| author | Sabry, Mohammed Khalifa, Amr M. A. |
| author_facet | Sabry, Mohammed Khalifa, Amr M. A. |
| contents | The breakthrough of deep Q-Learning on different types of environments revolutionized the algorithmic design of Reinforcement Learning to introduce more stable and robust algorithms, to that end many extensions to deep Q-Learning algorithm have been proposed to reduce the variance of the target values and the overestimation phenomena. In this paper, we examine new methodology to solve these issues, we propose using Dropout techniques on deep Q-Learning algorithm as a way to reduce variance and overestimation. We also present experiments conducted on benchmark environments, demonstrating the effectiveness of our methodology in enhancing stability and reducing both variance and overestimation in model performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1910_05983 |
| institution | arXiv |
| publishDate | 2019 |
| record_format | arxiv |
| spellingShingle | On the Reduction of Variance and Overestimation of Deep Q-Learning Sabry, Mohammed Khalifa, Amr M. A. Machine Learning The breakthrough of deep Q-Learning on different types of environments revolutionized the algorithmic design of Reinforcement Learning to introduce more stable and robust algorithms, to that end many extensions to deep Q-Learning algorithm have been proposed to reduce the variance of the target values and the overestimation phenomena. In this paper, we examine new methodology to solve these issues, we propose using Dropout techniques on deep Q-Learning algorithm as a way to reduce variance and overestimation. We also present experiments conducted on benchmark environments, demonstrating the effectiveness of our methodology in enhancing stability and reducing both variance and overestimation in model performance. |
| title | On the Reduction of Variance and Overestimation of Deep Q-Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/1910.05983 |