Identifying the Best Transition Law
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912235724472320 |
|---|---|
| author | Ahmadipour, Mehrasa Crepon, élise Garivier, Aurélien |
| author_facet | Ahmadipour, Mehrasa Crepon, élise Garivier, Aurélien |
| contents | Motivated by recursive learning in Markov Decision Processes, this paper studies best-arm identification in bandit problems where each arm's reward is drawn from a multinomial distribution with a known support. We compare the performance { reached by strategies including notably LUCB without and with use of this knowledge. } In the first case, we use classical non-parametric approaches for the confidence intervals. In the second case, where a probability distribution is to be estimated, we first use classical deviation bounds (Hoeffding and Bernstein) on each dimension independently, and then the Empirical Likelihood method (EL-LUCB) on the joint probability vector. The effectiveness of these methods is demonstrated through simulations on scenarios with varying levels of structural complexity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12227 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Identifying the Best Transition Law Ahmadipour, Mehrasa Crepon, élise Garivier, Aurélien Machine Learning Artificial Intelligence Motivated by recursive learning in Markov Decision Processes, this paper studies best-arm identification in bandit problems where each arm's reward is drawn from a multinomial distribution with a known support. We compare the performance { reached by strategies including notably LUCB without and with use of this knowledge. } In the first case, we use classical non-parametric approaches for the confidence intervals. In the second case, where a probability distribution is to be estimated, we first use classical deviation bounds (Hoeffding and Bernstein) on each dimension independently, and then the Empirical Likelihood method (EL-LUCB) on the joint probability vector. The effectiveness of these methods is demonstrated through simulations on scenarios with varying levels of structural complexity. |
| title | Identifying the Best Transition Law |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2502.12227 |