Evasive Active Hypothesis Testing with Deep Neuroevolution: The Single- and Multi-Agent Cases
Not on the map. Why?
Abstract (arXiv)
Active hypothesis testing is a thoroughly studied problem that finds numerous applications in wireless communications and sensor networks. In this paper, we focus on one centralized and one decentralized problem of active hypothesis testing in the presence of an eavesdropper. For the centralized problem including a single legitimate agent, we present a new framework based on deep NeuroEvolution (NE), whereas, for the decentralized problem, we develop a novel NE-based method for solving collaborative multi-agent tasks, which, interestingly, maintains all computational benefits of our single-agent NE-based scheme. To further reduce the computational complexity of the latter scheme, a novel multi-agent joint NE and pruning framework is also designed. The superiority of the proposed NE-based evasive active hypothesis testing schemes over conventional active hypothesis testing policies, as well as learning-based methods, is validated through extensive numerical investigations in an example use case of anomaly detection over wireless sensor networks. It is demonstrated that the proposed joint optimization and pruning framework achieves nearly identical performance with its unpruned counterpart, while removing a very large percentage of redundant deep neural network weights.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 35 of its 78 references that are in the map. First posted on arXiv 15 Mar 2024.
Builds on
35 of 78 references.
References · 35
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
- 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
- 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
- 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
- 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
- 2020What is the State of Neural Network Pruning?cited by 583
- 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 574
- 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 567
- 2013The Complexity of Decentralized Control of Markov Decision Processescited by 231
- 2021Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharingcited by 87
23 more
- 2019Machine Learning at the Network Edge: A Surveycited by 84
- 2022The State of Sparse Training in Deep Reinforcement Learningcited by 61
- 2021Dynamic Sparse Training for Deep Reinforcement Learningcited by 49
- 2021Deep Multiagent Reinforcement Learning: Challenges and Directionscited by 42
- 2018Back to Basics: Benchmarking Canonical Evolution Strategies for Playing Ataricited by 28
- 2017Internet of Things: An Overviewcited by 14
- 2023Parameter Sharing with Network Pruning for Scalable Multi-Agent Deep Reinforcement Learningcited by 14
- 2018Policy Design for Active Sequential Hypothesis Testing using Deep Learningcited by 13
- 2019Deep Actor-Critic Reinforcement Learning for Anomaly Detectioncited by 12
- 2020Privacy-Aware Time-Series Data Sharing with Deep Reinforcement Learningcited by 12
- 2022Pervasive Machine Learning for Smart Radio Environments Enabled by Reconfigurable Intelligent Surfacescited by 12
- 2021Active Sensing for Communications by Learningcited by 9
- 2023The Test of Tests: A Framework For Differentially Private Hypothesis Testingcited by 9
- 2020Anomaly Detection Under Controlled Sensing Using Actor-Critic Reinforcement Learningcited by 8
- 2021Bandit Quickest Changepoint Detectioncited by 7
- 2023Active Sensing for Localization with Reconfigurable Intelligent Surfacecited by 6
- 2021Scalable and Decentralized Algorithms for Anomaly Detection via Learning-Based Controlled Sensingcited by 4
- 2023Active hypothesis testing in unknown environments using recurrent neural networks and model free reinforcement learningcited by 4
- 2022Temporal Detection of Anomalies via Actor-Critic Based Controlled Sensingcited by 2
- 2022Active Sampling of Multiple Sources for Sequential Estimationcited by 2
- 2023Anomaly Detection via Learning-Based Sequential Controlled Sensingcited by 2
- 2016State Estimation with Secrecy against Eavesdropperscited by 1
- 2022Active Privacy-Utility Trade-off Against Inference in Time-Series Data Sharingcited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.