Cited by 1,353Cloud Computing and Resource ManagementDistributed and Parallel Computing SystemsEnergy Efficiency in Computing

The DOI matches its Crossref record; 40 of the 41 references it cites were found in a registry or an index.

Resource Management with Deep Reinforcement Learning

Mao, Hongzi, Alizadeh, Mohammad, Menache, Ishai, Kandula, Srikanth·2016·Proceedings of the 15th ACM Workshop on Hot Topics in Networks

DOI 10.1145/3005745.3005750

Open this paper in CoChat — free account

Abstract

Resource management problems in systems and networking often manifest as difficult online decision making tasks where appropriate solutions depend on understanding the workload and environment. Inspired by recent advances in deep reinforcement learning for AI problems, we consider building systems that learn to manage resources directly from experience. We present DeepRM, an example solution that translates the problem of packing tasks with multiple resource demands into a learning problem. Our initial results show that DeepRM performs comparably to state-of-the-art heuristics, adapts to different conditions, converges quickly, and learns strategies that are sensible in hindsight.

Integrity signals

Registry

Crossref · 10.1145/3005745.3005750

Cites

40 of 40 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Human-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357
Reinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. (2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.842673 · Cited by 25,268
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
Monte Carlo sampling methods using Markov chains and their applications.
Hastings, W. K. (1970) · Biometrika · doi:10.1093/biomet/57.1.97 · Cited by 15,195
Playing Atari with Deep Reinforcement Learning
Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., & Riedmiller, M. (2013) · arXiv · doi:10.48550/arxiv.1312.5602 · Cited by 9,471
A view of cloud computing
Armbrust, M., Fox, A., Griffith, R., Joseph, A. D., Katz, R., Konwinski, A., Lee, G., Patterson, D., Rabkin, A., Stoica, I., et al. (2010) · Communications of the ACM · doi:10.1145/1721654.1721672 · Cited by 9,464
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., et al. (2016) · arXiv · doi:10.48550/arxiv.1603.04467 · Cited by 9,408
Reinforcement Learning: A Survey
Kaelbling, L. P., Littman, M. L., & Moore, A. W. (1996) · Journal of Artificial Intelligence Research · doi:10.1613/jair.301 · Cited by 8,972
Asynchronous Methods for Deep Reinforcement Learning
Mnih, V., Badia, A. P., Mirza, M., Graves, A., Lillicrap, T. P., Harley, T., Silver, D., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1602.01783 · Cited by 7,132
Introduction to Reinforcement Learning
Sutton, R. S., & Barto, A. G. (1998) · The MIT Press eBooks · Cited by 6,855

Show all 41 references

Research works printed but not linked: 20

Agarwal S., 2012, NSDI, 281
Ananthanarayanan G., 2010, In OSDI, number, 1, 24
Bertsekas D. P., 1995, Decision and Control
Chilimbi T., 2014, OSDI, 571
Dong M., 2015, NSDI, 395
Ghodsi A., 2011, NSDI'11, 323
Heller B., 2010, NSDI'10
Junchen J., 2015, SIGCOMM '15
Kaelbling L. P., 1996, Journal of artificial intelligence research
Mahadevan S., 1998, FLAIRS Conference
Mnih V., 2016, CoRR
Mnih V., 2013, CoRR
Mnih V., 2015, Nature
J. Schulman S. Levine P. Moritz M. I. Jordan and P. Abbeel. Trust region policy optimization. CoRR abs/1502.05477 2015. J. Schulman S. Levine P. Moritz M. I. Jordan and P. Abbeel. Trust region policy optimization. CoRR abs/1502.05477 2015. · arXiv
10.5555/551283 · DOI
Sutton R. S., 1999, NIPS
Winstein K., 2013, NSDI, 459
Yi S., 2016, SIGCOMM
Yin X., 2016, SIGCOMM '16
Zhang W., 1995, IJCAI. Citeseer

Sorted by citations

Items 901–1,000 of 1,000

Knowledge-defined networking : a machine learning based approach for network and traffic modeling
Mestres, A. (2017) · doi:10.5821/dissertation-2117-114449 · Cited by 2
Stochastic Substitute Training: A Gray-box Approach to Craft Adversarial Examples Against Gradient Obfuscation DefensesPreprint
Hashemi, M., Cusack, G., & Keller, E. R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.10031 · Cited by 2
“3270111 defeating the best human players in the game of Go [31], making a humanoid robot run [30], and resource management in a cluster with different resource types [21].”
Background
Advancements of Deep Q-NetworksPreprint
Birkeneder, B. (2019) · viXra · Cited by 2
Optimizing Redundancy Levels in Master-Worker Compute Clusters for Straggler MitigationPreprint
Aktaş, M. F., & Soljanin, E. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.05345 · Cited by 2
“, [34]–[38].”
Orchestrating Development Lifecycle of Machine Learning Based IoT Applications: A Survey.Preprint
Qian, B., Su, J., Wen, Z., Jha, D. N., Li, Y., Guan, Y., Puthal, D., James, P., Yang, R., Zomaya, A. Y., et al. (2019) · arXiv (Cornell University) · Cited by 2
Novel applications of Machine Learning to Network Traffic Analysis and Prediction
Martín, M. L. (2019) · doi:10.35376/10324/39457 · Cited by 2
Towards A Domain-Customized Automated Machine Learning Framework For Networks and SystemsPreprint
Arzani, B., & Rouhani, B. D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.11931 · Cited by 5
“Today, building such models requires someone with expertise in both domains (networking/systems and ML) to select the model, engineer features, identify corner cases where the model can fail, and optimize the model for performance and scale [1, 5, 21, 23–28].”
Latency and Throughput Optimization in Modern Networks: A Comprehensive SurveyPreprint
Mirzaeinia, A., Mirzaeinia, M., & Rezgui, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.03715 · Cited by 12
Multi-Agent Deep Reinforcement Learning for Request Dispatching in Distributed-Controller Software-Defined NetworkingPreprint
Huang, V., Chen, G., & Fu, Q. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.03022 · Cited by 2
“Recently, machine learning has been successfully applied to various resource management problems [16]–[20].”
Influential
Differentiate Containers Scheduling for Deep Learning ApplicationsPreprint
Song, Y. J. (2020) · Preprints.org · doi:10.20944/preprints202011.0017.v1 · Cited by 2
“Besides human’s efforts, DeepRM [37] shows that machine learning itself can provide a viable alternative to human-generated heuristics for resource management.”
Background
Supporting the transformation of a company's project management by elaborating an invariant-based project management maturity model and a causal predictive model between maturity criteria and project performance
Garzon, F. S. (2019) · theses.fr (ABES) · doi:10.70675/77dff9c9zde36z4f7dz8d53z9ed5c3fc83f2 · Cited by 1
An Online Planning Agent to Optimize the Policy of Resources Management
Shrivastava, A. D., Thakkar, A., & Chudasama, V. (2021) · Lecture notes in networks and systems · doi:10.1007/978-981-16-0733-2_33 · Cited by 1
Distributed Spatial-Temporal Demand and Topology Aware Resource Provisioning for Edge Cloud Services
Huynh, V. S. H., Radenkovic, M., & Wang, N. (2021) · International Conference on Fog and Mobile Edge Computing (FMEC) · doi:10.1109/fmec54266.2021.9732562 · Cited by 2
Fuzzy Reinforcement Learning for Canal Control
Shahverdi, K., Alamiyan-Harandi, F., & Maestre, J. M. (2022) · Studies in computational intelligence · doi:10.1007/978-981-19-2519-1_15 · Cited by 1
Utilization of Deep Reinforcement Learning for Discrete Resource Allocation Problem in Project Management – a Simulation Experiment
Wójcik, F. (2022) · Informatyka Ekonomiczna · doi:10.15611/ie.2022.1.05 · Cited by 1
Deep Determinantal Q-Learning with Role Aware
Han, K., Yue, X., Liu, W., & Zhan, J. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-36822-6_25 · Cited by 1
OpenData: A Framework to Train and Deploy ML Solutions in Wide-Area Networks
Keshvadi, S., Hu, S., Lian, Y., & Li, G. (2023) · IEEE Network · doi:10.1109/mnet.2023.3320929 · Cited by 1
“The majority of these problems are solved today using heuristic solutions that could become insufficient and unreliable if an aspect of the problem changes [7].”
Background
ERODRL: Efficient ISP Routing Optimization via Deep Reinforcement Learning
Chen, C., Chen, X., & Zeng, D. (2023) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa-bdcloud-socialcom-sustaincom59178.2023.00084 · Cited by 1
“Drawing inspiration from [13], we define the action space as { 1 , 2 , 3 , ..., N ∗ ( N − 1) } , which represents the probability of each flow being selected as the critical flow.”
Method
Formula-E Multi-Car Race Strategy Development—A Novel Approach Using Reinforcement Learning
Liu, X., Fotouhi, A., & Auger, D. J. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3389155 · Cited by 1
“RL-based meth-ods have been proven of great utilities in a wide variety of applications such as robotics [18], games [19], resource management [20], etc.”
Background
Efficient Cloud Cluster Resource Scheduling with Deep Reinforcement Learning
Liu, X., Dong, B., & Hao, F. (2023) · International Conference on Advanced Cloud and Big Data · doi:10.1109/cbd63341.2023.00015 · Cited by 1
Exploiting Anytime Algorithms for Collaborative Service Execution in Edge Computing
Nogueira, L., Coelho, J., & Pereira, D. (2024) · Computers · doi:10.3390/computers13060130 · Cited by 1
Restoration-Aware Sleep Scheduling Framework in Energy Harvesting Internet of Things: A Deep Reinforcement Learning Approach
Ko, H., Choi, H., & Pack, S. (2024) · IEEE Transactions on Sustainable Computing · doi:10.1109/tsusc.2024.3442918 · Cited by 1
Capacity-Aware Planning and Scheduling in Budget-Constrained Multi-Agent MDPs: A Meta-RL Approach
Vora, M., Shomorony, I., & Ornik, M. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3617726 · Cited by 1
“Our LSAP partitioning eliminates the nr joint-action explosion by decomposing the problem into r sub-MDPs.”
Online Job Scheduling for Energy Cost Optimization in Geo-Distributed Data Centers Considering Data Locality: A Multi-Agent Reinforcement Learning Approach
Lang, J., Zheng, X., Sun, Y., & Ding, Z. (2024) · IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia) · doi:10.1109/icpsasia61913.2024.10761284 · Cited by 1
“The action space is denoted as A j = { ( j 1 , C 1 ) , . . . , ( j j , C m ) , Φ } and respectively, where Φ correspondingly indicates that job scheduler does not assign any job to data centers and the scheduler does not transfer any data to data centers at the current time step [14].”
Leveraging Reinforcement Learning for Autonomous Data Pipeline Optimization and Management
Lekkala, C. (2023) · International Journal of Science and Research (IJSR) · doi:10.21275/sr24531190901 · Cited by 1
RL-Based Approach to Enhance Reliability and Efficiency in Autoscaling for Heterogeneous Edge Serverless Computing Environments
Hadjou, I., & Kwon, Y. (2024) · IEEE Pacific Rim International Symposium on Dependable Computing (PRDC) · doi:10.1109/prdc63035.2024.00046 · Cited by 1
“By leveraging reinforcement learning, we aim to develop an adaptive autoscaling mechanism that can dynamically adjust to real-time workload variations, thereby improving the overall dependability of the system[15].”
SK-CFR: Rerouting critical flows through discrete soft actor–critic within the KP-GNN framework
Zhang, L., Peng, S., & Dong, P. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111175 · Cited by 1
SVDE: Serverless Framework for Low-Latency Video Analytic Queries With Hardware Disaggregation
Huo, P., Michailidis, T., Zheng, Y., Panigrahi, P., Maeng, K., Zhao, J., & Narayanan, V. (2025) · IEEE Transactions on Computers · doi:10.1109/tc.2025.3569173 · Cited by 1
“…average) to capture the relative queue status between workers while prohibiting the raw value of the feature from becoming too large and make the training unstable [36]. d) Node Compute Power: Similar to prior works [5], SVDE also takes the computational capability of each node as an input feature.”
Flora: Efficient Cloud Resource Selection for Big Data Processing Via Job Classification
Will, J., Thamsen, L., Bader, J., & Kao, O. (2025) · IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid) · doi:10.1109/ccgrid64434.2025.00020 · Cited by 1
“Several approaches for automated cluster resource selection rely on the assumption that jobs are recurring to continuously enhance performance models with each job execution [4], [13]–[17].”
Deep Learning Training Job Scheduling for Proactive Straggler Reduction
Shen, H., & Zhang, Z. (2025) · IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid) · doi:10.1109/ccgrid64434.2025.00038 · Cited by 1
Federated learning with three-way decisions for privacy-preserving multicloud resource scheduling
Jiang, C., & Su, L. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113634 · Cited by 1
SCAN: ML-Based Slice Congestion and Admission Network Controller
Perveen, A., Bulut, B., Abozariba, R., Patwary, M., Aneiba, A., Jindal, A., & Al-Kadri, M. O. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3592803 · Cited by 1
“In addition, reinforcement learning (RL) has been applied to wireless network management [23], [24], [25], [26], [27], but current approaches suffer from scalability and computational complexity limitations.”
Deep Reinforcement Learning for Autonomous Cost and Performance Optimization of Big Data Query Engines in the Cloud
Jarsania, J., Harsh, F., Singh, M. P., & Behl, S. (2025) · IEEE World AI IoT Congress (AIIoT) · doi:10.1109/aiiot65859.2025.11105305 · Cited by 1
Understanding Linux Kernel-Based Packet Switching on WiFi Access Points
Zhang, S., Gupta, M., & Dezfouli, B. (2025) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2025.3603597 · Cited by 1
“Such statistics can also be leveraged by machine learning methods to dynamically tune system parameters [6], [24], [25], [26], [27].”
A Transformer-embedded Reinforcement Learning for Computing Power Scheduling in Data Centers
Zhou, H., Cui, G., & Jia, Q. (2025) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case58245.2025.11164014 · Cited by 1
“[20] presents DeepRM, a solution framework that formulates the task packing problem with multi-resource demands as a learning problem, and results demonstrate that DRL outperforms the state-of-art heuristics.”
DAF: An Efficient End-to-End Dynamic Activation Framework for on-Device DNN Training
Liu, R., Leng, Y., Liu, K., Hu, S., Chen, R., Zhao, P., Yun, H., & Yao, S. (2025) · International Conference on Mobile Systems, Applications, and Services · doi:10.1145/3711875.3729145 · Cited by 2
“We adopted the reinforcement learning-based method from DeepRM [48] as our baseline and evaluated three memory increment strategies, corresponding to small (30 MB), proper (100 MB), and large (400 MB) allocation steps.”
AIMS: An Adaptive Intelligent Multi-Objective Scheduler Powered by Digital Twins
Adimora, K. C., & Sun, H. (2025) · IEEE High Performance Extreme Computing Conference · doi:10.1109/hpec67600.2025.11196586 · Cited by 1
“Mao et al. [19] demonstrated RL effectiveness in cloud resource allocation.”
Knowledge Defined Networking for 6G: A Reinforcement Learning Example for Resource Management
Bilen, T., Özdem, M., & Koçoğlu, E. (2025) · doi:10.1109/ubmk67458.2025.11206750 · Cited by 1
“Accordingly, Mao et al. [4] present DeepRM, a deep reinforcement learning (DRL) framework for dynamic resource allocation in clusters.”
Design and Implementation of Integrated AI Scheduler for Dynamic Cloud Workloads Allocation in Kubernetes Environments
Bidollahkhani, M., Sharma, A. K., Nanavati, S. P., Ardebili, M. S., Mamulashvili, G., Aydin, M., Stein, F. O., Akbari, M., & Kunkel, J. M. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-07986-2_25 · Cited by 1
Dynamic Resource Allocation and Optimization in Cloud Computing Using Reinforcement Learning and Federated Learning Techniques
Sakthivel, T. G., Murugesan, R., & Anitha, G. (2025) · doi:10.1109/iccds64403.2025.11209376 · Cited by 1
“An example of this would be Mao et al. (2016), who presented a framework for dynamic resource scaling in cloud settings that was based on reinforcement learning.”
Fine-Grained Scheduling Strategies and Optimization of Wind–Solar–Storage Powered Data Center Microgrids
Dong, C., Liu, H., Qi, Y., Li, B., & Zhang, F. (2025) · IEEE Access · doi:10.1109/access.2025.3641756 · Cited by 1
Dynamic Predictive Feedback Mechanism for Intelligent Bandwidth Control in Future SDN Networks
Somsuk, K., Khummanee, S., & Songram, P. (2025) · Network · doi:10.3390/network5040054 · Cited by 1
“These limitations motivate architectures such as DPF, which explicitly combine telemetry-driven feedback loops with learned traffic prediction and meta-level adaptation, all integrated into the SDN control plane [17,19,24,31].”
Influential
Energy-Efficient Task Scheduling in Data Centers Using Adaptive Deep Reinforcement Learning
Dinuț, I.-C., Alexandrescu, B., & Constantinescu, R. (2025) · International Conference on Energy Efficiency and Agricultural Engineering (EE&AE) · doi:10.1109/eeae65901.2025.11273693 · Cited by 1
“While heuristic methods remain relevant benchmarks, the literature increasingly supports RL-based approaches as superior for dynamic environments, with foundational works like DeepRM by Mao et al. showing early promise [8].”
A Novel Hybrid Grey Wolf Whale Optimization for Effectual Job Scheduling and Resource Distribution in Dynamic Cloud Computing
Sukumar, H. K. K. (2025) · International Conference on Sustainability, Innovation & Technology (ICSIT) · doi:10.1109/icsit65336.2025.11293898 · Cited by 1
AI-Driven Cloud Infrastructure Provisioning: Leveraging Machine Learning, Observability, and IaC for Autonomous Cloud Operations
Mehla, A., Dahiya, N., & Singh, K. (2025) · International Conference on Emerging Trends in Networks and Computer Communications (ETNCC) · doi:10.1109/etncc66224.2025.11299663 · Cited by 1
AI-Enhanced Routing Optimization for SDN/NFV Architectures in Large-Scale IoT Networks
Hatim, J., Bouhaddour, S., Belghiti, I. D., Saadi, C., & Chaoui, H. (2025) · International Conference on Wireless Networks and Mobile Communications (WINCOM) · doi:10.1109/wincom65874.2025.11313390 · Cited by 1
Threshold-Triggered Heuristic-Assisted Deep Reinforcement Learning for Elastic and QoS-Guaranteed 5G RAN Slice Migration
Gu, J., Zhu, M. Y., Wang, Y., Dong, B., Kong, L., Li, R., Cai, Y., Zhang, J., & Huang, Y. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3649984 · Cited by 1
Energy-Aware Job Profiling and Mediation for Cloud and 6G Orchestration
Chawla, H., Fallon, S., & Fallon, E. (2025) · International Conference on 6G Networking (6GNet) · doi:10.1109/6gnet68413.2025.11314128 · Cited by 1
“…vs. deadline adherence; (v) explore learning-to-schedule (contextual bandits/RL) with safety constraints and fairness to priority classes [18]; and (vi) assess applicability in telecom-edge scenarios aligned with 6G, including co-optimization of compute and RAN power budgets [19], [20].”
Enhancing High-Performance Computing with Artificial Intelligence: A Comprehensive Analysis of AI-Driven Solutions for Optimizing Resource Management, Performance, and Reliability
Pol, V., & Singal, S. M. (2025) · International Conference on Applied Artificial Intelligence and Computing (ICAAIC) · doi:10.1109/icaaic64647.2025.11330359 · Cited by 1
Intelligent Kubernetes Scheduling with Large Language Models
Bai, X., Tang, Z., Yao, Z., Chen, Y., Guo, J., Wang, T., & Weijia Jia, B. (2025) · IEEE International Conference on Security, Privacy, Anonymity in Computation, Communication and Storage (SpaCCS) · doi:10.1109/spaccs67922.2025.00012 · Cited by 3
“Before LLMs, AI-driven scheduling mainly involved ML techniques requiring extensive training or complex reward design, such as QoS-aware prediction with collaborative filtering [9], Reinforcement Learning with MDPs [5], [8], or GNN-based resource forecasting [24].”
Heuristic-Guided Multi-Agent Reinforcement Learning for Computing Service Scheduling in Distributed Data Centers
Zhao, Y., Wang, C., Yan, C., Li, X., & Jiang, C. (2026) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2026.3656552 · Cited by 1
Adaptive Edge Intelligence for Efficient Task Offloading in Dynamic Networks
Singh, R. (2025) · International Conference on Mobile Networks and Wireless Communications (ICMNWC) · doi:10.1109/icmnwc66779.2025.11354357 · Cited by 1
“Unlike heuristic or optimization-based methods, the RL agent improves its decision policy over time, continuously adapting to dynamic conditions [5], [12].”
Proactive Autoscaling for Cloud-Native Applications Using Predictive Resource Allocation
Kumar, B., Verma, A., & Verma, P. (2025) · Studies in autonomic, data-driven and industrial computing · doi:10.1007/978-3-032-12972-7_10 · Cited by 1
AI-Driven Optimization of Backend and Cloud Infrastructure in Large-Scale Financial Systems
Mishra, V. K. (2026) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-31286 · Cited by 2
Dynamic SFC Mapping and Time Scheduling With Store-and-Forward Scheme Based on DRL in Inter-Datacenter Elastic Optical Networks
Wang, Y., Kong, L., Zhu, M., Gu, J., Cai, Y., & Zhang, J. (2026) · IEEE Transactions on Networking · doi:10.1109/ton.2026.3674479 · Cited by 1
“• PG Algorithm [46]: The PG method is used as a baseline algorithm, which leverages the cumulative discounted reward to update the policy.”
TPSTA: A Tissue P System-Inspired Task Allocator for Heterogeneous Multi-Core Systems
Zhang, Y., & Ji, Z. (2026) · Electronics · doi:10.3390/electronics15061339 · Cited by 1
An Intelligent Energy-Efficient Computing Framework Using Machine Learning-Driven Optimization for Sustainable
Surendar, A., Kavitha, M., & Rajan, C. (2026) · International Conference on Sentiment Analysis and Deep Learning (ICSADL) · doi:10.1109/icsadl67539.2026.11451854 · Cited by 1
“This paper addresses these challenges by coming up with an intelligent energy saving computing platform using reinforcement learning in the aspects of energy control dynamism in sustainable community smart systems [4], [5], [7].”
Influential
Adaptive Load Balancing for Multi-Tier LLM Inference with Dynamic Model Routing
Patel, T., Kulkarni, C., Shivam, S., Padhy, A. K., Ranganathan, V., & Bayyavarapu, S. R. K. V. (2026) · IEEE SoutheastCon · doi:10.1109/southeastcon63549.2026.11476301 · Cited by 1
“Reinforcement learning for load balancing has been applied to web services [18], batch job scheduling [19], [31], and video streaming [20].”
Deep reinforcement learning driven by offset-attention mechanism for intelligent manufacturing cloud service composition and optimal selection
Wang, S., Liu, L., Zhu, M., Zhao, J., Yang, Z., & Li, C. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114925 · Cited by 1
Reinforcement Learning-Based QoS Allocation for Diverse Network Environments with Security Constraints
Gowtham, S., Hari Prashanth, S., & Kalaiarasi, G. (2026) · International Conference on Augmented Intelligence and Sustainable Systems (ICAISS) · doi:10.1109/icaiss68683.2026.11526458 · Cited by 1
“…provides three largely independent foundations: (i) reinforcement learning for adaptive resource allocation and QoS optimization [1], [3], [7], [16], [17], [20], (ii) encrypted traffic classification without payload inspection [8], [9], [14], [15], [18], and (iii) trust-aware or…”
Multiobjective task scheduling in cloud computing using hybrid algorithm (HRLM)
Gupta, S., & Arora, S. (2026) · Simulation Modelling Practice and Theory · doi:10.1016/j.simpat.2026.103305 · Cited by 1
SIA: Symbolic Interpretability for Anticipatory Deep Reinforcement Learning in Network Control
Jabbari, M., Duttagupta, A., Fiandrino, C., Bonati, L., D’Oro, S., Polese, M., Fiore, M., & Melodia, T. (2026) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom59046.2026.11571259 · Cited by 1
“Deep Reinforcement Learning (DRL) is a promising approach for adaptive network control, with proven successes in resource allocation [3], [4], scheduling [5], [6], and parameter optimization [7], [8].”
Enhancing Mobile Multitasking with Reinforcement Learning-Based Attention Management
Lingler, A., Frijns, H. A., Silva, N., Ebel, P., & Wintersberger, P. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2688492 · Cited by 3
PRESAGE: Uncertainty-Aware Predictive Elastic Scheduling for Cloud Analytics and GenAI Inference
Wang, Y., Zou, X., Zhou, L., Wei, K., & Rhee, M. (2026) · IEEE Access · doi:10.1109/access.2026.3734498 · Cited by 3
Deep Learning Cluster Structures for Management Decisions: The Digital CEO
Serrano, W. (2018) · Sensors · doi:10.3390/s18103327 · Cited by 1
Scalable Network Design and Management with Decentralized Software-defined Networking
Atwal, K. S. (2019) · Journal of International Crisis and Risk Communication Research · Cited by 1
Research Programs Based on Machine Intelligence Games
Tamburrini, G., & Altiero, F. (2020) · Philosophy of engineering and technology · doi:10.1007/978-3-030-54522-2_11 · Cited by 1
Policy Gradient Method based Energy Efficience Task Scheduling in Mobile Edge Blockchain
Yin, Y., Wu, W., Dong, J., Yang, G., Yang, S., & Zhang, Y. (2020) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc51575.2020.9344967 · Cited by 1
“The update parameter θ function is expressed as follows [10] [11]”
Method
О ПРОБЛЕМЕ СБОРА ДАННЫХ В СЕТЯХ ИНТЕРНЕТА ВЕЩЕЙ С ДИНАМИЧЕСКОЙ СТРУКТУРОЙ
Жукова, Н. А., Tristanov, A. B., Tun, T. A., & Аунг, М. Т. (2021) · KSTU News · doi:10.46845/1997-3071-2021-61-105-118 · Cited by 1
Study on the Path Planning Algorithm Based on Dueling Deep Q Network
Cao, J., Zhao, S., Guo, C., Hu, Y., Gao, Q., Shen, F., Ye, Y., & Zhang, Y. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1920/1/012084 · Cited by 1
“At present, DQN has shown its magic power in different fields: defeating top human players in video games[12] and chess and card games[13]; controlling complex machines [14], and allocating network resources[15].”
Background
Task Distribution and Human Resource Management Using Reinforcement Learning
Păduraru, C., Paduraru, M. G., & Patilea, C. (2021) · IEEE/ACM International Conference on Automated Software Engineering Workshops (ASEW) · doi:10.1109/asew52652.2021.00029 · Cited by 1
Neuroshard
Eldeeb, T., Chen, Z., Cidon, A., & Yang, J. (2022) · International Workshop on Exploiting Artificial Intelligence Techniques for Data Management (aiDM) · doi:10.1145/3533702.3534908 · Cited by 1
“Like prior work [27], we utilize a class of RL algorithms in Neuroshard learns by performing gradient descent over the policy parameters.”
BackgroundMethodResultInfluential
Multi-Resource Scheduling for Multiple Service Function Chains with Deep Reinforcement Learning
He, R., Ren, B., Xie, J., Guo, D., & Zhao, L. (2023) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads56603.2022.00092 · Cited by 1
Distance-aware Multi-Agent Reinforcement Learning for Task Offloading in MEC Network
Jiang, L., Sun, L., & Zhu, W. (2022) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc-dss-smartcity-dependsys57074.2022.00085 · Cited by 1
“We deliberately design our task generator to allocate the task for each terminal user u i , and the task sequence follows Binomial Distribution [13].”
Method
Learning Enabled Data Center Operation Scheme for Participating in Power Market
Chen, S., Sun, Y., Liu, W., & Ding, Z. (2023) · IEEE/IAS Industrial and Commercial Power Systems Technical Conference · doi:10.1109/icps57144.2023.10142076 · Cited by 1
“The resource requirements, computing durations, deadline and income settings are as shown in Table I [24].”
Method
Implementation of an Effective Framework in Merging Cybersecurity and Software Engineering
Alhuqail, S. K., & Jamail, N. S. M. (2023) · International Women in Data Science Conference at Prince Sultan University (WiDS PSU) · doi:10.1109/wids-psu57071.2023.00019 · Cited by 1
A Novel Deep Q-Network-Based Scheme for Online Virtual Link Embedding in Software Defined Networks
Tan, X.-D., Du, J., Chen, L., & Liu, W. (2023) · International Conference on Cloud Computing and Big Data Analytics (ICCCBDA) · doi:10.1109/icccbda56900.2023.10154874 · Cited by 1
“With dynamic user requests and constantly changing substrate physical network conditions, it becomes increasingly difficult to develop a decent VL embedding scheme [6].”
Background
Heterogeneous Multi-Robot Task Allocation for Garment Transformable Production using Deep Reinforcement Learning
Neto, R. P. B., Ohno, K., Kojima, S., Aryadi, H. A., Gunji, K., Kuwahara, M., Okada, Y., Konyo, M., & Tadokoro, S. (2023) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case56687.2023.10260437 · Cited by 1
“For instance, DeepRM is a DRL-based scheduler that minimizes the average job completion time for single-cluster jobs with heterogeneous resources [16].”
Background
Cost Efficient Job Scheduling Scheme for Large Scale Data Center
Li, X., & Ding, Z. (2023) · IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia) · doi:10.1109/icpsasia58343.2023.10294452 · Cited by 1
“For instance, DQN has been used in literature [10], [11] to select the optimal action for job-server matching, while the policy gradient algorithm has been employed in literature [12] to choose the best strategy for scheduling jobs at each time step.”
Method
Energy-Aware Data Center Job Scheduling Scheme under Uncertain Environment
Shi, K., Chen, S., Chen, S., Sun, Y., & Ding, Z. (2024) · IEEE/IAS Industrial and Commercial Power Systems Technical Conference · doi:10.1109/icps60943.2024.10563375 · Cited by 1
“Mao et al. [9] formulated the task scheduling problem as a reinforcement learning (RL) problem and proposed resource management with DRL to optimize various objectives, transforming the task of packing tasks with multiple resource demands into a learning problem.”
Method
A Multi-agent Reinforcement Learning Based CR Allocation Approach For Multi-Scenario Advertising Systems
Liu, C., Ye, Y., Zhang, L., Fan, R., Chen, Y., Zhang, K., & Chan, W. K. V. (2024) · IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC) · doi:10.1109/imcec59810.2024.10575234 · Cited by 2
“Works including DeepRM [14], cellular network traffic scheduling [13], GreenDRL [11], and DRL for edge computing [15] have successfully utilized deep reinforcement learning, including multi-agent deep reinforcement learning, to address resource allocation, traffic control as well as edge computing…”
Method
Causal Deep Q Networks
Khelifi, E., Saki, A., & Faghihi, U. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-4677-4_21 · Cited by 1
ETPAM: An Efficient Task Pre-Assignment and Migration Algorithm in Heterogeneous Edge-Cloud Computing Environments
Zhang, F., Jiang, L., & Chen, J. (2024) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd61410.2024.10580834 · Cited by 1
Can Tricks Affect Robustness of Multi-Agent Reinforcement Learning?
Li, X., Ju, P., & Jing, Z. (2024) · Chinese Control Conference (CCC) · doi:10.23919/ccc63176.2024.10662305 · Cited by 1
Effective Strategies for the Teamwork Scheduling Problem with Job-Person Constraint
Long, H. X., Son, T. H., Pham, H.-A., & Tuong, N. H. (2024) · Asia Pacific Conference on Innovation in Technology (APCIT) · doi:10.1109/apcit62007.2024.10673498 · Cited by 1
“DQN has achieved impressive results on resource management problems [7], suggesting promise for application to scheduling problems.”
Background
Adaptive Clustering and Step-Size Optimization in Collaborative Distributed Diffusion-Based AIGC: Balancing Performance and Resource Utilization
Xu, Z., Kim, D. I., & Woo, S. S. (2024) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc62082.2024.10826855 · Cited by 1
Intelligent Resource Allocation in Cloud Computing Environments: Leveraging Machine Learning for Dynamic Workload Balancing, Cost Efficiency, and Performance Optimization
Haroon, F. (2025) · Annual Methodological Archive Research Review · doi:10.63075/gdxsyd86 · Cited by 1
“Reinforcement learning (RL) strategies have also been employed as the agents learn the best resource allocation strategies through trial and error within the environment whereby the performance of the system is either rewarded positively or punished (Mao et al., 2016).”
A learnable dynamic scheduling for directed graph jobs flow in heterogeneous supercomputing clusters
Wang, L., Zhou, J., & Liu, W. (2025) · Future Generation Computer Systems · doi:10.1016/j.future.2025.108047 · Cited by 1
Scheduling virtual machines and containers: A comparative review of techniques, performance, and future trends
Zhao, N., Wang, H., Yang, F., Zhang, J., Wu, R., Zhong, T., Han, S., Huang, Z., Zhang, X., & Zhao, X. (2025) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2025.103583 · Cited by 1
Soft-set based DDQ scheduler for Optimal Task Scheduling under Uncertainty in the Cloud
Bhargavi, K., & Babu, B. S. (2017) · International Conference on Emerging Computation and Information Technologies (ICECIT) · doi:10.1109/icecit.2017.8453306 · Cited by 1
“Deep reinforcement learning based resource management scheme in the cloud is discussed in [14].”
Background
Deep Reinforcement Learning Based Policy for Power Efficient Dynamic Subcarrier Assignment in OFDMA-PONs
Chen, B., Zhu, M., Gu, J., Shen, T., Ren, X., & Shi, C. (2019) · Cited by 1
Metareasoning in Modular Software Systems: On-the-Fly Configuration Using Reinforcement Learning with Rich Contextual Representations
Modi, A., Dey, D., Agarwal, A., Swaminathan, A., Nushi, B., Andrist, S., & Horvitz, E. (2020) · AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) · doi:10.1609/aaai.v34i04.5965 · Cited by 1
Fault Diagnosis for the Virtualized Network in the Cloud Environment using Reinforcement Learning
Xu, T., Shen, D., Zhang, H., Xiong, R., & Jin, J. (2019) · IEEE International Conference on Smart Cloud (SmartCloud) · doi:10.1109/smartcloud.2019.00047 · Cited by 1
“Addressing this challenge, we leverage the method of reinforcement learning [6] to facilitate the fault diagnosis in the cloud environment, where we diagnose the faults through an “exploration and exploitation” manner.”
Method
Policy Return: A New Method for Reducing the Number of Experimental Trials in Deep Reinforcement Learning
Liu, F., Dai, S., & Zhao, Y. (2020) · IEEE Access · doi:10.1109/access.2020.3045835 · Cited by 1
“…learning have achieved excellent performances across various domains, for instance, beating the top human players in Go matches [3], [4], controlling the operation of complex machinery [5]–[8], allocating network resources [9], improving wireless communication technologies [10], [11], etc.”
Background
Learning Coflow Admissions
Hasnain, A., & Karl, H. (2021) · IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · doi:10.1109/infocomwkshps51825.2021.9484599 · Cited by 1
Machine Learning Application in the Hybrid Optical Wireless Networks
Naik, D., & De, T. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-981-15-9516-5_41 · Cited by 1
A Genetic Algorithm based task scheduling procedure for Cost-Efficient Cloud Data Centers
Prabha, B., Ramesh, K., & Geetha, A. (2021) · International Conference on Advanced Scientific Innovation in Science, Engineering and Technology (ICASISET) · doi:10.4108/eai.16-5-2020.2303974 · Cited by 1
Guiding Representation Learning in Deep Generative Models with Policy Gradients
Lach, L., Korthals, T., Ferro, F., Ritter, H. J., & Schilling, M. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-85672-4_9 · Cited by 1
Vehicular Edge Computing via Deep Reinforcement Learning
Qi, Q., & Ma, Z. (2019) · arXiv · doi:10.48550/arxiv.1901.04290 · Cited by 17
“Mao et al. [21] ﬁnding the optimal resource management policy by DRL.”
Background
Applications of Deep Reinforcement Learning in Communications and Networking: A Survey
Luong, N. C., Hoang, D. T., Gong, S., Niyato, D., Wang, P., Liang, Y.-C., & Kim, D. I. (2018) · arXiv · doi:10.48550/arxiv.1810.07862 · Cited by 17
“The authors in [163] propose a DRL-based solution, DeepRM, by employing policy gradient methods [148] to manage resources in computer systems directly from experience.”
Method

Authors: Mao, H., Alizadeh, M., Menache, I., & Kandula, S.
Affiliations: Massachusetts Institute of Technology (US)
Microsoft (United States) (US)
ORCID: Alizadeh, Mohammad
Menache, Ishai
Kandula, Srikanth
Venue: Proceedings of the 15th ACM Workshop on Hot Topics in Networks
Publisher: ACM
Published: 2016-11-09
Pages: 50-56
DOI: 10.1145/3005745.3005750
OpenAlex: W2546571074
Cited by: 1,353
References: 41
Citations by year: 2026: 171 · 2025: 181 · 2024: 98 · 2023: 140 · 2022: 151 · 2021: 191 · 2020: 180 · 2019: 155 · 2018: 62 · 2017: 24
FWCI: 68.24
Type: conference paper
Language: en
Open access: closed
Licence: www.acm.org/publications/policies/copyright_policy#Background (vor)
Locations: ACM Workshop on Hot Topics in Networks (HotNets) (publishedVersion)
Topics: Physical Sciences › Computer Science › Information Systems › Cloud Computing and Resource Management
Physical Sciences › Computer Science › Computer Networks and Communications › Distributed and Parallel Computing Systems
Physical Sciences › Computer Science › Hardware and Architecture › Energy Efficiency in Computing
Keywords: resource management, deep reinforcement learning, task scheduling, resource allocation, workload modeling, online decision making, experiential learning

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Resource Management with Deep Reinforcement Learning

Abstract

Overview

Integrity signals

Verification

Claims the paper makes

Claims other papers make about this one

Citations

Cites

Cited by

Related

Metadata

Record

About these checks