Learning Index Selection with Structured Action Spaces

TL;DR

This paper introduces a structured action space approach for index selection in databases, leveraging permutation learning and task-specific biases to improve efficiency and effectiveness over traditional RL methods.

Contribution

It proposes a novel permutation-based action representation for index selection, enhancing deep RL with task-specific inductive biases for better performance.

Findings

Achieves up to 40% smaller index configurations at the same latency

Demonstrates improved indexing behavior and efficiency

Validates approach with early experimental results

Abstract

Configuration spaces for computer systems can be challenging for traditional and automatic tuning strategies. Injecting task-specific knowledge into the tuner for a task may allow for more efficient exploration of candidate configurations. We apply this idea to the task of index set selection to accelerate database workloads. Index set selection has been amenable to recent applications of vanilla deep RL, but real deployments remain out of reach. In this paper, we explore how learning index selection can be enhanced with task-specific inductive biases, specifically by encoding these inductive biases in better action structures. Index selection-specific action representations arise when the problem is reformulated in terms of permutation learning and we rely on recent work for learning RL policies on permutations. Through this approach, we build an indexing agent that is able to achieve improved indexing and validate its behavior with task-specific statistics. Early experiments reveal that our agent can find configurations that are up to 40% smaller for the same levels of latency as compared with other approaches and indicate more intuitive indexing behavior.