# Anomaly Detection via Learning-Based Sequential Controlled Sensing

arXiv: https://arxiv.org/abs/2312.00088 · HTML: https://mlsanity.com/paper/2312.00088/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 30 references that are in the map.
- First posted on arXiv 30 Nov 2023.

## Builds on (most cited first, 11 of 11)

- [Dueling Network Architectures for Deep Reinforcement Learning](https://mlsanity.com/paper/1511.06581/) (2015)
- [Deep Active Inference as Variational Policy Gradients](https://mlsanity.com/paper/1907.03876/) (2019)
- [Policy Design for Active Sequential Hypothesis Testing using Deep Learning](https://mlsanity.com/paper/1810.04859/) (2018)
- [Deep Actor-Critic Reinforcement Learning for Anomaly Detection](https://mlsanity.com/paper/1908.10755/) (2019)
- [Anomaly Detection Under Controlled Sensing Using Actor-Critic Reinforcement Learning](https://mlsanity.com/paper/2006.01044/) (2020)
- [Scalable and Decentralized Algorithms for Anomaly Detection via Learning-Based Controlled Sensing](https://mlsanity.com/paper/2112.04912/) (2021)
- [A Scalable Algorithm for Anomaly Detection via Learning-Based Controlled Sensing](https://mlsanity.com/paper/2105.06289/) (2021)
- [Anomaly Detection via Controlled Sensing and Deep Active Inference](https://mlsanity.com/paper/2105.06288/) (2021)
- [Temporal Detection of Anomalies via Actor-Critic Based Controlled Sensing](https://mlsanity.com/paper/2201.00879/) (2022)
- [Optimal Stopping for Interval Estimation in Bernoulli Trials](https://mlsanity.com/paper/1711.06912/) (2017)
- [Model-based actor-critic: GAN (model generator) + DRL (actor-critic) => AGI](https://mlsanity.com/paper/2004.04574/) (2020)

## Built on by (most cited first, 2 of 2)

- [Evasive Active Hypothesis Testing with Deep Neuroevolution: The Single- and Multi-Agent Cases](https://mlsanity.com/paper/2403.10112/) (2024)
- [On Cost-Aware Designs for Sequential Hypothesis Testing](https://mlsanity.com/paper/2512.19067/) (2025)

## Abstract (arXiv)

In this paper, we address the problem of detecting anomalies among a given set of binary processes via learning-based controlled sensing. Each process is parameterized by a binary random variable indicating whether the process is anomalous. To identify the anomalies, the decision-making agent is allowed to observe a subset of the processes at each time instant. Also, probing each process has an associated cost. Our objective is to design a sequential selection policy that dynamically determines which processes to observe at each time with the goal to minimize the delay in making the decision and the total sensing cost. We cast this problem as a sequential hypothesis testing problem within the framework of Markov decision processes. This formulation utilizes both a Bayesian log-likelihood ratio-based reward and an entropy-based reward. The problem is then solved using two approaches: 1) a deep reinforcement learning-based approach where we design both deep Q-learning and policy gradient actor-critic algorithms; and 2) a deep active inference-based approach. Using numerical experiments, we demonstrate the efficacy of our algorithms and show that our algorithms adapt to any unknown statistical dependence pattern of the processes.