Learning State Representations for Query Optimization with Deep Reinforcement Learning
Explore this paper's citation graph
Summary
This paper focuses specifically on the state representation problem and the formation of the state transition function and shows preliminary results and discusses how to use the state represented to improve query optimization using reinforcement learning.
- Type
- preprint
- Published
- 2018-03-22
- Cited by
- 171
- References
- 20
- Access
- Open access
- OpenAlex
- https://openalex.org/W2795239330
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:4245127
Keywords
Reinforcement learning, Computer science, Representation (politics), Artificial intelligence, State (computer science)
References
- SQL Server数据复制（上）
- Algorithms for Reinforcement Learning
- LEO - DB2's LEarning Optimizer
- Reinforcement Learning: An Introduction
- Human-level control through deep reinforcement learning
- Rk-hist: an r-tree based histogram for multi-dimensional selectivity estimation
- Eddies: continuously adaptive query processing
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- How Good Are Query Optimizers, Really?
- Cardinality estimation using neural networks
- Sampling-Based Query Re-Optimization
- Database Meets Deep Learning: Challenges and Opportunities
- A Reinforcement Learning Approach for Adaptive Query Processing
- Cardinality Estimation Done Right: Index-Based Join Sampling
- Estimating Join Selectivities using Bandwidth-Optimized Kernel Density Models
- The Case for Learned Index Structures
- State Representation Learning for Control: An Overview
- Deep Reinforcement Learning for Join Order Enumeration
- Deep Learning
- Deep Learning
Cited by
- Deep Reinforcement Learning for Join Order Enumeration
- Software-Defined Software: A Perspective of Machine Learning-Based Software Production
- Learning to Optimize Join Queries With Deep Reinforcement Learning
- Learned Cardinalities: Estimating Correlated Joins with Deep Learning
- Guided automated learning for query workload re-optimization
- Plan-Structured Deep Neural Network Models for Query Performance Prediction
- Flexible Operator Embeddings via Deep Learning
- SageDB: A Learned Database System
- Learned Indexes for Dynamic Workloads
- Opportunistic View Materialization with Deep Reinforcement Learning
- How I Learned to Stop Worrying and Love Re-optimization
- Approximate Query Processing using Deep Generative Models
- Multi-Attribute Selectivity Estimation Using Deep Learning
- Interpolation-friendly B-trees: Bridging the Gap Between Algorithmic and Learned Indexes
- A Vision of a Decisional Model for Re-optimizing Query Execution Plans Based on Machine Learning Techniques
- NeuralCubes: Deep Representations for Visual Data Exploration
- Estimating Cardinalities with Deep Sketches
- Selectivity Estimation with Deep Likelihood Models
- ALEX: An Updatable Adaptive Learned Index
- Cardinality estimation with local deep learning models
Related papers
- Learned Cardinalities: Estimating Correlated Joins with Deep Learning
- Deep Reinforcement Learning for Join Order Enumeration
- Learning to Optimize Join Queries With Deep Reinforcement Learning
- How Good Are Query Optimizers, Really?
- Towards a Hands-Free Query Optimizer through Deep Learning
- Access path selection in a relational database management system
- Automatic Database Management System Tuning Through Large-scale Machine Learning
- Cardinality estimation using neural networks
- Learning-based Query Performance Modeling and Prediction