Generalized Rapid Action Value Estimation in Memory-Constrained Environments
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917297191387136 |
|---|---|
| author | Rautureau, Aloïs Cazenave, Tristan Piette, Éric |
| author_facet | Rautureau, Aloïs Cazenave, Tristan Piette, Éric |
| contents | Generalized Rapid Action Value Estimation (GRAVE) has been shown to be a strong variant within the Monte-Carlo Tree Search (MCTS) family of algorithms for General Game Playing (GGP). However, its reliance on storing additional win/visit statistics at each node makes its use impractical in memory-constrained environments, thereby limiting its applicability in practice. In this paper, we introduce the GRAVE2, GRAVER and GRAVER2 algorithms, which extend GRAVE through two-level search, node recycling, and a combination of both techniques, respectively. We show that these enhancements enable a drastic reduction in the number of stored nodes while matching the playing strength of GRAVE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_23318 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Generalized Rapid Action Value Estimation in Memory-Constrained Environments Rautureau, Aloïs Cazenave, Tristan Piette, Éric Artificial Intelligence Generalized Rapid Action Value Estimation (GRAVE) has been shown to be a strong variant within the Monte-Carlo Tree Search (MCTS) family of algorithms for General Game Playing (GGP). However, its reliance on storing additional win/visit statistics at each node makes its use impractical in memory-constrained environments, thereby limiting its applicability in practice. In this paper, we introduce the GRAVE2, GRAVER and GRAVER2 algorithms, which extend GRAVE through two-level search, node recycling, and a combination of both techniques, respectively. We show that these enhancements enable a drastic reduction in the number of stored nodes while matching the playing strength of GRAVE. |
| title | Generalized Rapid Action Value Estimation in Memory-Constrained Environments |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2602.23318 |