Time-critical and confidence-based abstraction dropping methods
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908432125132800 |
|---|---|
| author | Schmöcker, Robin Kampmann, Lennart Dockhorn, Alexander |
| author_facet | Schmöcker, Robin Kampmann, Lennart Dockhorn, Alexander |
| contents | One paradigm of Monte Carlo Tree Search (MCTS) improvements is to build and use state and/or action abstractions during the tree search. Non-exact abstractions, however, introduce an approximation error making convergence to the optimal action in the abstract space impossible. Hence, as proposed as a component of Elastic Monte Carlo Tree Search by Xu et al., abstraction algorithms should eventually drop the abstraction. In this paper, we propose two novel abstraction dropping schemes, namely OGA-IAAD and OGA-CAD which can yield clear performance improvements whilst being safe in the sense that the dropping never causes any notable performance degradations contrary to Xu's dropping method. OGA-IAAD is designed for time critical settings while OGA-CAD is designed to improve the MCTS performance with the same number of iterations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_02703 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Time-critical and confidence-based abstraction dropping methods Schmöcker, Robin Kampmann, Lennart Dockhorn, Alexander Artificial Intelligence One paradigm of Monte Carlo Tree Search (MCTS) improvements is to build and use state and/or action abstractions during the tree search. Non-exact abstractions, however, introduce an approximation error making convergence to the optimal action in the abstract space impossible. Hence, as proposed as a component of Elastic Monte Carlo Tree Search by Xu et al., abstraction algorithms should eventually drop the abstraction. In this paper, we propose two novel abstraction dropping schemes, namely OGA-IAAD and OGA-CAD which can yield clear performance improvements whilst being safe in the sense that the dropping never causes any notable performance degradations contrary to Xu's dropping method. OGA-IAAD is designed for time critical settings while OGA-CAD is designed to improve the MCTS performance with the same number of iterations. |
| title | Time-critical and confidence-based abstraction dropping methods |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2507.02703 |