Automating Feature Subspace Exploration via Multi-Agent Reinforcement Learning

Liu, Kunpeng; Fu, Yanjie; Wang, Pengfei; Wu, Le; Bo, Rui; Li, Xin

doi:10.1145/3292500.3330868

Cited by 46 publications

(49 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A reward is assigned to the agent based on the predictive performance of the current features subset. Liu et al [17] propose a method to reformulate feature engineering as a multi-agent reinforcement learning problem. The multiagent RL formulation reduces the large action space of a single agent since now each of the agents has a smaller action space for one feature selection.…”

Section: Feature Engineeringmentioning

confidence: 99%

“…However, this formu-lation also brings challenges: interactions between agents, representation of the environment, and selection of samples. Three technical methods in [17] have been proposed to tackle them respectively: adding inter-feature information to reward formulation, using meta statistics, and deep learning methods to learn the representation of the environment, and Gaussian mixture to independently determine samples. However, although this formulation reduces the action space, the trade-off is using more computing resources to support more agents' learning.…”

Section: Feature Engineeringmentioning

confidence: 99%

“…Notably, DRL incorporates deep learning (DL) techniques to handle complex unstructured data and has been designed to learn from historical data and self-exploration to solve notoriously hard and large-scale problems (e.g., AlphaGo [15]). In recent years, researchers from different communities have proposed DRL solutions to address issues in data processing and analytics [4], [16], [17]. We categorize existing works using DRL from two perspectives: system and application.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Survey on Deep Reinforcement Learning for Data Processing and Analytics

Cai

Cui

Xiong

et al. 2022

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Data processing and analytics are fundamental and pervasive. Algorithms play a vital role in data processing and analytics where many algorithm designs have incorporated heuristics and general rules from human knowledge and experience to improve their effectiveness. Recently, reinforcement learning, deep reinforcement learning (DRL) in particular, is increasingly explored and exploited in many areas because it can learn better strategies in complicated environments it is interacting with than statically designed algorithms. Motivated by this trend, we provide a comprehensive review of recent works focusing on utilizing DRL to improve data processing and analytics. First, we present an introduction to key concepts, theories, and methods in DRL. Next, we discuss DRL deployment on database systems, facilitating data processing and analytics in various aspects, including data organization, scheduling, tuning, and indexing. Then, we survey the application of DRL in data processing and analytics, ranging from data preparation, natural language processing to healthcare, fintech, etc. Finally, we discuss important open challenges and future research directions of using DRL in data processing and analytics.

show abstract

Section: Feature Engineeringmentioning

confidence: 99%

Section: Feature Engineeringmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Deep Reinforcement Learning for Data Processing and Analytics

Cai

Cui

Xiong

et al. 2022

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

show abstract

“…A reward is assigned to the agent based on the predictive performance of the current features subset. Liu et al [52] propose a method to reformulate feature engineering as a multi-agent reinforcement learning problem. The multi-agent RL formulation reduces the large action space of a single agent since now each of the agents has a smaller action space for one feature selection.…”

Section: Feature Engineeringmentioning

confidence: 99%

A Survey on Deep Reinforcement Learning for Data Processing and Analytics

Cai¹,

Cui²,

Xiong³

et al. 2021

Preprint

View full text Add to dashboard Cite

Data processing and analytics are fundamental and pervasive. Algorithms play a vital role in data processing and analytics where many algorithm designs have incorporated heuristics and general rules from human knowledge and experience to improve their effectiveness. Recently, reinforcement learning, deep reinforcement learning (DRL) in particular, is increasingly explored and exploited in many areas because it can learn better strategies in complicated environments it is interacting with than statically designed algorithms. Motivated by this trend, we provide a comprehensive review of recent works focusing on utilizing deep reinforcement learning to improve data processing and analytics. First, we present an introduction to key concepts, theories, and methods in deep reinforcement learning. Next, we discuss deep reinforcement learning deployment on database systems, facilitating data processing and analytics in various aspects, including data organization, scheduling, tuning, and indexing. Then, we survey the application of deep reinforcement learning in data processing and analytics , ranging from data preparation, natural language interface to healthcare, fintech, etc. Finally, we discuss important open challenges and future research directions of using deep reinforcement learning in data processing and analytics.

show abstract

“…[19] Liao et al proposed Multi-objective Optimization by Reinforcement Learning (MORL) to solve the optimal power system dispatch and voltage stability problem, which is undertaken on individual dimension in a high-dimensional space via a path selected by an estimated path value which represents the potential of finding a better solution [9] . Liu et al reformulated the feature selection problem into a multi-agent reinforcement learning framework where the selection of each feature is controlled by its corresponding feature agent [5,11]. Yang et al developed deep reinforcement learning algorithms which could handle large scale agents with effective communication protocol [16,24].…”

Section: Reinforcement Learningmentioning

confidence: 99%

Ambulance Dispatch via Deep Reinforcement Learning

Liu

Zou

et al. 2020

Proceedings of the 28th International Conference on Advances in Geographic Information Systems

Self Cite

View full text Add to dashboard Cite

In this paper, we solve the ambulance dispatch problem with a reinforcement learning oriented strategy. The ambulance dispatch problem is defined as deciding which ambulance to pick up which patient. Traditional studies on ambulance dispatch mainly focus on predefined protocols and are verified on simple simulation data, which are not flexible enough when facing the dynamically changing real-world cases. In this paper, we propose an efficient ambulance dispatch method based on the reinforcement learning framework, i.e., Multi-Agent Q-Network with Experience Replay(MAQR). Specifically, we firstly reformulate the ambulance dispatch problem with a multi-agent reinforcement learning framework, and then design the state, action, and reward function correspondingly for the framework. Thirdly, we design a simulator that controls ambulance status, generates patient requests and interacts with ambulances. Finally, we design extensive experiments to demonstrate the superiority of the proposed method. CCS CONCEPTS • Computing methodologies → Multi-agent reinforcement learning; • Information systems → Spatial-temporal systems.

show abstract

Automating Feature Subspace Exploration via Multi-Agent Reinforcement Learning

Cited by 46 publications

References 23 publications

A Survey on Deep Reinforcement Learning for Data Processing and Analytics

A Survey on Deep Reinforcement Learning for Data Processing and Analytics

A Survey on Deep Reinforcement Learning for Data Processing and Analytics

Ambulance Dispatch via Deep Reinforcement Learning

Contact Info

Product

Resources

About