RELOAD: A Robust and Efficient Learned Query Optimizer for Database Systems
Not on the map. Why?
Abstract (arXiv)
Recent advances in query optimization have shifted from traditional rule-based and cost-based techniques towards machine learning-driven approaches. Among these, reinforcement learning (RL) has attracted significant attention due to its ability to optimize long-term performance by learning policies over query planning. However, existing RL-based query optimizers often exhibit unstable performance at the level of individual queries, including severe performance regressions, and require prolonged training to reach the plan quality of expert, cost-based optimizers. These shortcomings make learned query optimizers difficult to deploy in practice and remain a major barrier to their adoption in production database systems. To address these challenges, we present RELOAD, a robust and efficient learned query optimizer for database systems. RELOAD focuses on (i) robustness, by minimizing query-level performance regressions and ensuring consistent optimization behavior across executions, and (ii) efficiency, by accelerating convergence to expert-level plan quality. Through extensive experiments on standard benchmarks, including Join Order Benchmark, TPC-DS, and Star Schema Benchmark, RELOAD demonstrates up to 2.4x higher robustness and 3.1x greater efficiency compared to state-of-the-art RL-based query optimization techniques.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 41 references that are in the map. First posted on arXiv 16 Apr 2026.
Builds on
19 of 41 references.
References · 19
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2015Prioritized Experience Replaycited by 1,099
- 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
- 2020Towards Continual Reinforcement Learning: A Review and Perspectivescited by 274
- 2020Transfer Learning in Deep Reinforcement Learning: A Surveycited by 265
- 2019Neo: A Learned Query Optimizercited by 80
- 2020Bao: Learning to Steer Query Optimizerscited by 62
- 2021Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Taskscited by 36
- 2018Learning to Optimize Join Queries With Deep Reinforcement Learningcited by 32
- 2023Lero: A Learning-to-Rank Query Optimizercited by 26
- 2018Deep Reinforcement Learning for Join Order Enumerationcited by 25
- 2022Balsa: Learning a Query Optimizer Without Expert Demonstrationscited by 18
7 more
- 2018Learning State Representations for Query Optimization with Deep Reinforcement Learningcited by 14
- 2021A Survey on Advancing the DBMS Query Optimizer: Cardinality Estimation, Cost Model, and Plan Enumerationcited by 14
- 2018Towards a Hands-Free Query Optimizer through Deep Learningcited by 8
- 2021How to distribute data across tasks for meta-learning?cited by 7
- 2023Is Your Learned Query Optimizer Behaving As You Expect? A Machine Learning Perspectivecited by 3
- 2023FOSS: A Self-Learned Doctor for Query Optimizercited by 1
- 2025LIMAO: A Framework for Lifelong Modular Learned Query Optimizationcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025SEFRQO: A Self-Evolving Fine-Tuned RAG-Based Query Optimizer
- 2025AutoIndexer: A Reinforcement Learning-Enhanced Index Advisor Towards Scaling Workloads
- 2024Learned Graph Rewriting with Equality Saturation: A New Paradigm in Relational Query Rewrite and Beyond
- 2025BQSched: A Non-intrusive Scheduler for Batch Concurrent Queries via Reinforcement Learning
- 2025ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL
- 2025Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL
- 2024The Unreasonable Effectiveness of LLMs for Query Optimization
- 2026Beyond Static Pipelines: Learning Dynamic Workflows for Text-to-SQL