---
title: "Generalized Rapid Action Value Estimation"
authors:
  - "Tristan Cazenave"
doi: ""
url: "https://ijcai.org/proceedings/2015/112"
pdf: "https://ijcai.org/proceedings/2015/0112.pdf"
venue: "Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence"
year: 2015
pages: "754-759"
track: "Main Track"
keywords:
---

# Generalized Rapid Action Value Estimation

Tristan Cazenave

*Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence*, pages 754-759.

## Abstract

Monte Carlo Tree Search (MCTS) is the state of the art algorithm for many games including the game of Go and General Game Playing (GGP). The standard algorithm for MCTS is Upper Confidence bounds applied to Trees (UCT). For games such as Go a big improvement over UCT is the Rapid Action Value Estimation (RAVE) heuristic. We propose to generalize the RAVE heuristic so as to have more accurate estimates near the leaves. We test the resulting algorithm named GRAVE for Atarigo, Knighthrough, Domineering and Go.