Generalized Rapid Action Value Estimation in Memory-Constrained Environments

2026/02/26 by Aloïs Rautureau, Tristan Cazenave, Éric Piette · 1 voice
Computer Science · #cs.AI

paper · pdf · doi:10.48550/arxiv.2602.23318

Abstract

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.

Citations

• Aligning Superhuman AI with Human Behavior: Chess as a Model System
• Ludii -- The Ludemic General Game System
• Approximate is Better than “Exact” for Interval Estimation of Binomial Proportions
• Human Memory: A Proposed System and its Control Processes
• The magical number seven, plus or minus two: Some limits on our capacity for processing information.

Discussions

• 📖 New LAMSADE preprint: Generalized Rapid Action Value Estimation in Memory-Constrained Environments. (arXiv) https://doi.org/10.48550/arXiv.2602.23318 [bsky, 0 points, 0 comments]

Related

• Monte Carlo Tree Search with Heuristic Evaluations using Implicit Minimax Backups
• Monte Carlo Permutation Search
• Proof Number Based Monte-Carlo Tree Search
• Playing Carcassonne with Monte Carlo Tree Search
• Monte Carlo Game Solver