# Generalized Rapid Action Value Estimation in Memory-Constrained Environments

arXiv: https://arxiv.org/abs/2602.23318 · HTML: https://mlsanity.com/paper/2602.23318/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 24 references that are in the map.
- First posted on arXiv 26 Feb 2026.

## Builds on (most cited first, 2 of 2)

- [Aligning Superhuman AI with Human Behavior: Chess as a Model System](https://mlsanity.com/paper/2006.01855/) (2020)
- [Ludii -- The Ludemic General Game System](https://mlsanity.com/paper/1905.05013/) (2019)

## Abstract (arXiv)

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.