Join Order Selection with Deep Reinforcement Learning: Fundamentals, Techniques, and Challenges

Summary: Tutorial surveys deep-RL join-order selection, relating approaches and contrasting their strengths with traditional optimization. Two open-source demonstrations and a synthesis of challenges highlight directions toward practical, experience-driven query optimization. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID: 13407
Venue: VLDB
Year: 2023
Pagerank: 5.7878855e-05
Overall Rank: 6,735 | 53.80%
DOI: 10.14778/3611540.3611576

Incoming Non-self Citations Over Time

Authors

1. Zhengtong Yan (University of Helsinki)
2. Valter Uotila (University of Helsinki)
3. Jiaheng Lu (University of Helsinki)

BibTeX Citation

@article{yan_vldb23,
        title = {{Join Order Selection with Deep Reinforcement Learning: Fundamentals, Techniques, and Challenges}},
        author = {Yan, Zhengtong and Uotila, Valter and Lu, Jiaheng},
        journal = {PVLDB},
        series = {{VLDB} '23},
        volume = {16},
        number = {12},
        pages = {3882--3885},
        doi = {10.14778/3611540.3611576},
        url = {https://doi.org/10.14778/3611540.3611576},
        year = {2023}
}

Incoming Citations (Sorted by Pagerank)

Showing 5 of 5 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
9,626	Spatial Query Optimization With Learning	2024	VLDB	5.2434488e-05
10,343	APQO: An Adaptive Framework for Parametric Query Optimization	2026	SIGMOD	5.093636e-05
10,559	OBELISK: Efficient Offline Query Planning with Bayesian Optimization-Informed Language Model Reasoning	2026	VLDB	5.093636e-05
10,749	AJOSC: Adaptive Join Order Selection for Continuous Queries	2025	SIGMOD	5.093636e-05
11,067	Machine Learning for Graph Data Management and Query Processing	2025	VLDB	5.093636e-05

Outgoing Citations (Sorted by Pagerank)

Showing 16 of 16 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
1	Access Path Selection in a Relational Database Management System	1979	SIGMOD	0.0024089429
18	How Good Are Query Optimizers, Really?	2016	VLDB	0.00059284255
154	Neo: A Learned Query Optimizer	2019	VLDB	0.00028726181
378	Bao: Making Learned Query Optimization Practical	2021	SIGMOD	0.00019638121
774	Rapid Bushy Join-order Optimization with Cartesian Products	1996	SIGMOD	0.00014123979
1,013	Dynamic Programming Strikes Back	2008	SIGMOD	0.00012652549
1,241	Balsa: Learning a Query Optimizer Without Expert Demonstrations	2022	SIGMOD	0.00011521639
1,286	Adaptive Optimization of Very Large Join Queries	2018	SIGMOD	0.00011320736
1,298	Analysis of Two Existing and One New Dynamic Programming Algorithm for the Generation of Optimal Bushy Join Trees without Cross Products	2006	VLDB	0.00011259156
1,712	SkinnerDB: Regret-Bounded Query Evaluation via Reinforcement Learning	2019	SIGMOD	9.9492299e-05
2,420	Lero: A Learning-to-Rank Query Optimizer	2023	VLDB	8.605257e-05
2,762	Cost-based or Learning-based? A Hybrid Query Optimizer for Query Plan Selection	2022	VLDB	8.1539867e-05
2,888	AI Meets Database: AI4DB and DB4AI	2021	SIGMOD	7.9941489e-05
3,516	LOGER: A Learned Optimizer towards Generating Efficient and Robust Query Execution Plans	2023	VLDB	7.3524442e-05
5,340	Machine Learning for Databases	2021	VLDB	6.2603359e-05
5,399	Efficient Massively Parallel Join Optimization for Large Queries*	2022	SIGMOD	6.2319315e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	3,813	Query Simplification: Graceful Degradation for Join-Order Optimization	2009	SIGMOD
2	1,712	SkinnerDB: Regret-Bounded Query Evaluation via Reinforcement Learning	2019	SIGMOD
3	1,286	Adaptive Optimization of Very Large Join Queries	2018	SIGMOD
4	3,516	LOGER: A Learned Optimizer towards Generating Efficient and Robust Query Execution Plans	2023	VLDB
5	11,909	Improving Join Reorderability with Compensation Operators	2018	SIGMOD
6	5,340	Machine Learning for Databases	2021	VLDB
7	3,051	Towards a Hands-Free Query Optimizer through Deep Learning	2019	CIDR
8	7,882	Efficiently Computing Join Orders with Heuristic Search	2023	SIGMOD
9	7,978	ADOPT: Adaptively Optimizing Attribute Orders for Worst-Case Optimal Join Algorithms via Reinforcement Learning	2023	VLDB
10	11,497	Demonstrating ADOPT: Adaptively Optimizing Attribute Orders for Worst-Case Optimal Joins via Reinforcement Learning	2023	VLDB