A Reinforcement Learning Approach to Online Learning of Decision Trees

TL;DR

This paper introduces RLDT, a reinforcement learning-based method for online decision tree learning that minimizes feature queries, adapts to concept drift, and matches the performance of traditional algorithms.

Contribution

RLDT is a novel online decision tree algorithm that uses reinforcement learning to reduce feature queries and improve long-term classification performance.

Findings

RLDT performs comparably to batch and online algorithms.

RLDT makes significantly fewer feature queries.

RLDT effectively handles concept drift.

Abstract

Online decision tree learning algorithms typically examine all features of a new data point to update model parameters. We propose a novel alternative, Reinforcement Learning- based Decision Trees (RLDT), that uses Reinforcement Learning (RL) to actively examine a minimal number of features of a data point to classify it with high accuracy. Furthermore, RLDT optimizes a long term return, providing a better alternative to the traditional myopic greedy approach to growing decision trees. We demonstrate that this approach performs as well as batch learning algorithms and other online decision tree learning algorithms, while making significantly fewer queries about the features of the data points. We also show that RLDT can effectively handle concept drift.