# UDO: Universal Database Optimization using Reinforcement Learning

arXiv: https://arxiv.org/abs/2104.01744 · HTML: https://mlsanity.com/paper/2104.01744/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Apr 2021.

## Built on by (most cited first, 11 of 11)

- [E2ETune: End-to-End Knob Tuning via Fine-tuned Generative Language Model](https://mlsanity.com/paper/2404.11581/) (2024)
- [VDTuner: Automated Performance Tuning for Vector Data Management Systems](https://mlsanity.com/paper/2404.10413/) (2024)
- [A Unified and Efficient Coordinating Framework for Autonomous DBMS Tuning](https://mlsanity.com/paper/2303.05710/) (2023)
- [Can Deep Neural Networks Predict Data Correlations from Column Names?](https://mlsanity.com/paper/2107.04553/) (2021)
- [Procrastinated Tree Search: Black-box Optimization with Delayed, Noisy, and Multi-Fidelity Feedback](https://mlsanity.com/paper/2110.07232/) (2021)
- [ML-Powered Index Tuning: An Overview of Recent Progress and Open Challenges](https://mlsanity.com/paper/2308.13641/) (2023)
- [Budget-aware Query Tuning: An AutoML Perspective](https://mlsanity.com/paper/2404.00137/) (2024)
- [Action Shapley: A Training Data Selection Metric for World Model in Reinforcement Learning](https://mlsanity.com/paper/2601.10905/) (2026)
- [DemoTuner: Automatic Performance Tuning for Database Management Systems Based on Demonstration Reinforcement Learning](https://mlsanity.com/paper/2511.09998/) (2025)
- [DOT: Dynamic Knob Selection and Online Sampling for Automated Database Tuning](https://mlsanity.com/paper/2603.15540/) (2026)
- [Reinforcement Learning based DBMS Buffer Pool Auto-Tuning for Optimal Memory Utilization](https://mlsanity.com/paper/2608.11239/) (2026)

## Abstract (arXiv)

UDO is a versatile tool for offline tuning of database systems for specific workloads. UDO can consider a variety of tuning choices, reaching from picking transaction code variants over index selections up to database system parameter tuning. UDO uses reinforcement learning to converge to near-optimal configurations, creating and evaluating different configurations via actual query executions (instead of relying on simplifying cost models). To cater to different parameter types, UDO distinguishes heavy parameters (which are expensive to change, e.g. physical design parameters) from light parameters. Specifically for optimizing heavy parameters, UDO uses reinforcement learning algorithms that allow delaying the point at which the reward feedback becomes available. This gives us the freedom to optimize the point in time and the order in which different configurations are created and evaluated (by benchmarking a workload sample). UDO uses a cost-based planner to minimize reconfiguration overheads. For instance, it aims to amortize the creation of expensive data structures by consecutively evaluating configurations using them. We evaluate UDO on Postgres as well as MySQL and on TPC-H as well as TPC-C, optimizing a variety of light and heavy parameters concurrently.