Generalized Rapid Action Value Estimation in Memory-Constrained Environments

2026-02-26

AI Summary

This work addresses the challenge of deploying the GRAVE algorithm in memory-constrained environments, where its substantial storage overhead poses a significant barrier. To overcome this limitation, the authors propose three enhanced variants—GRAVE2, GRAVER, and GRAVER2—that integrate, for the first time, a two-layer search structure with a node recycling mechanism within the GRAVE framework. Built upon Monte Carlo Tree Search, these methods employ efficient pruning and node reuse strategies to drastically reduce the number of stored nodes while preserving the original algorithm’s competitive performance. Experimental results on general game-playing tasks demonstrate that the proposed approaches achieve win rates comparable to those of the original GRAVE, effectively striking a balance between memory efficiency and decision quality.

Technology Category

• Search and Optimization: Adversarial Search
• Machine Learning: Graph-based Machine Learning
• Multiagent Systems: Adversarial Agents

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

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.

Problem

• GRAVE
• memory-constrained environments
• Monte-Carlo Tree Search
• General Game Playing

Innovation

• GRAVE2
• node recycling
• two-level search
• memory-constrained environments
• Monte-Carlo Tree Search