Analysis of Value Iteration Through Absolute Probability Sequences
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912221302358016 |
|---|---|
| author | Mustafin, Arsenii Colla, Sebastien Olshevsky, Alex Paschalidis, Ioannis Ch. |
| author_facet | Mustafin, Arsenii Colla, Sebastien Olshevsky, Alex Paschalidis, Ioannis Ch. |
| contents | Value Iteration is a widely used algorithm for solving Markov Decision Processes (MDPs). While previous studies have extensively analyzed its convergence properties, they primarily focus on convergence with respect to the infinity norm. In this work, we use absolute probability sequences to develop a new line of analysis and examine the algorithm's convergence in terms of the $L^2$ norm, offering a new perspective on its behavior and performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_03244 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Analysis of Value Iteration Through Absolute Probability Sequences Mustafin, Arsenii Colla, Sebastien Olshevsky, Alex Paschalidis, Ioannis Ch. Machine Learning Value Iteration is a widely used algorithm for solving Markov Decision Processes (MDPs). While previous studies have extensively analyzed its convergence properties, they primarily focus on convergence with respect to the infinity norm. In this work, we use absolute probability sequences to develop a new line of analysis and examine the algorithm's convergence in terms of the $L^2$ norm, offering a new perspective on its behavior and performance. |
| title | Analysis of Value Iteration Through Absolute Probability Sequences |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2502.03244 |