PMCTS: Particle Monte Carlo Tree Search for Principled Parallelized Inference Time Scaling
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911704102731776 |
|---|---|
| author | Oren, Yaniv Vadocz, Viliam de Vries, Joery A. Böhmer, Wendelin Spaan, Matthijs T. J. Baier, Hendrik |
| author_facet | Oren, Yaniv Vadocz, Viliam de Vries, Joery A. Böhmer, Wendelin Spaan, Matthijs T. J. Baier, Hendrik |
| contents | Monte Carlo Tree Search (MCTS) is a widely used approach for policy improvement through search with increasing popularity for real world applications. Due to the sequential and deterministic nature of its search, runtime-scaling of MCTS with parallel compute remains a major challenge. We introduce Particle MCTS (PMCTS), to our knowledge the first principled parallel MCTS algorithm which is suited for neural network evaluations and can preserve formal policy improvement guarantees. Empirically, PMCTS scales well with parallel compute and significantly outperforms the popular heuristic-based baselines across domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_08982 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PMCTS: Particle Monte Carlo Tree Search for Principled Parallelized Inference Time Scaling Oren, Yaniv Vadocz, Viliam de Vries, Joery A. Böhmer, Wendelin Spaan, Matthijs T. J. Baier, Hendrik Machine Learning Monte Carlo Tree Search (MCTS) is a widely used approach for policy improvement through search with increasing popularity for real world applications. Due to the sequential and deterministic nature of its search, runtime-scaling of MCTS with parallel compute remains a major challenge. We introduce Particle MCTS (PMCTS), to our knowledge the first principled parallel MCTS algorithm which is suited for neural network evaluations and can preserve formal policy improvement guarantees. Empirically, PMCTS scales well with parallel compute and significantly outperforms the popular heuristic-based baselines across domains. |
| title | PMCTS: Particle Monte Carlo Tree Search for Principled Parallelized Inference Time Scaling |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2605.08982 |