Markov decision processes: on the convergence of the Monte-Carlo first visit algorithm
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912597710733312 |
|---|---|
| author | Delattre, Sylvain Fournier, Nicolas |
| author_facet | Delattre, Sylvain Fournier, Nicolas |
| contents | We consider the Monte-Carlo first visit algorithm, of which the goal is to find the optimal control in a Markov decision process with finite state space and finite number of possible actions. We show its convergence when the discount factor is smaller than $1/2$. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_08800 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Markov decision processes: on the convergence of the Monte-Carlo first visit algorithm Delattre, Sylvain Fournier, Nicolas Probability Optimization and Control We consider the Monte-Carlo first visit algorithm, of which the goal is to find the optimal control in a Markov decision process with finite state space and finite number of possible actions. We show its convergence when the discount factor is smaller than $1/2$. |
| title | Markov decision processes: on the convergence of the Monte-Carlo first visit algorithm |
| topic | Probability Optimization and Control |
| url | https://arxiv.org/abs/2501.08800 |