# Learning Position Evaluation Functions Used in Monte Carlo Softmax Search

## TL;DR

This paper proposes new methods for Monte Carlo Softmax Search, including separate node-selection and backup policies, and introduces sampling-based learning for positional evaluation functions to improve efficiency and flexibility.

## Contribution

It introduces a novel framework for Monte Carlo Softmax Search with separate policies and sampling-based learning methods for evaluation functions, enhancing search strategy design and learning efficiency.

## Key findings

- Principal variations align with minimax search results.
- Sampling-based learning reduces the number of games needed for training.
- New learning rules improve evaluation function accuracy.

## Abstract

This paper makes two proposals for Monte Carlo Softmax Search, which is a recently proposed method that is classified as a selective search like the Monte Carlo Tree Search. The first proposal separately defines the node-selection and backup policies to allow researchers to freely design a node-selection policy based on their searching strategies and confirms the principal variation produced by the Monte Carlo Softmax Search to that produced by a minimax search. The second proposal modifies commonly used learning methods for positional evaluation functions. In our new proposals, evaluation functions are learned by Monte Carlo sampling, which is performed with the backup policy in the search tree produced by Monte Carlo Softmax Search. The learning methods under consideration include supervised learning, reinforcement learning, regression learning, and search bootstrapping. Our sampling-based learning not only uses current positions and principal variations but also the internal nodes and important variations of a search tree. This step reduces the number of games necessary for learning. New learning rules are derived for sampling-based learning based on the Monte Carlo Softmax Search and combinations of the modified learning methods are also proposed in this paper.

---
Source: https://tomesphere.com/paper/1901.10706