# Active Sensing for Communications by Learning

arXiv: https://arxiv.org/abs/2112.04075 · HTML: https://mlsanity.com/paper/2112.04075/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 48 references that are in the map.
- First posted on arXiv 8 Dec 2021.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://mlsanity.com/paper/1603.04467/) (2016)
- [Attention on Attention for Image Captioning](https://mlsanity.com/paper/1908.06954/) (2019)
- [A Decomposable Attention Model for Natural Language Inference](https://mlsanity.com/paper/1606.01933/) (2016)
- [Structured Attention Networks](https://mlsanity.com/paper/1702.00887/) (2017)
- [Towards Interpretable Reinforcement Learning Using Attention Augmented Agents](https://mlsanity.com/paper/1906.02500/) (2019)
- [Learning to Reflect and to Beamform for Intelligent Reflecting Surface with Implicit Channel Estimation](https://mlsanity.com/paper/2009.14404/) (2020)
- [Active Learning for Wireless IoT Intrusion Detection](https://mlsanity.com/paper/1808.01412/) (2018)
- [Rayleigh Fading Modeling and Channel Hardening for Reconfigurable Intelligent Surfaces](https://mlsanity.com/paper/2009.04723/) (2020)
- [Playing 20 Question Game with Policy-Based Reinforcement Learning](https://mlsanity.com/paper/1808.07645/) (2018)
- [Active Learning and CSI Acquisition for mmWave Initial Alignment](https://mlsanity.com/paper/1812.07722/) (2018)
- [Leveraging Location Information for RIS-aided mmWave MIMO Communications](https://mlsanity.com/paper/2010.14163/) (2020)
- [Sequential Learning of CSI for MmWave Initial Alignment](https://mlsanity.com/paper/1912.12738/) (2019)

## Built on by (most cited first, 9 of 9)

- [Statistical Hypothesis Testing Based on Machine Learning: Large Deviations Analysis](https://mlsanity.com/paper/2207.10939/) (2022)
- [Localization with Reconfigurable Intelligent Surface: An Active Sensing Approach](https://mlsanity.com/paper/2312.09002/) (2023)
- [Joint Active RIS Configuration and User Power Control for Localization: A Neuroevolution-Based Approach](https://mlsanity.com/paper/2510.13819/) (2025)
- [Evasive Active Hypothesis Testing with Deep Neuroevolution: The Single- and Multi-Agent Cases](https://mlsanity.com/paper/2403.10112/) (2024)
- [Large Deviations for Classification Performance Analysis of Machine Learning Systems](https://mlsanity.com/paper/2301.07104/) (2023)
- [Deep Reinforcement Learning for mmWave Initial Beam Alignment](https://mlsanity.com/paper/2302.08969/) (2023)
- [Transfer Learning with Reconstruction Loss](https://mlsanity.com/paper/2404.00505/) (2024)
- [Learning Beamforming Codebooks for Active Sensing with Reconfigurable Intelligent Surface](https://mlsanity.com/paper/2503.19046/) (2025)
- [Active Sensing for RIS-Aided Tracking and Power Control: A Hybrid Neuroevolution and Supervised Learning Approach](https://mlsanity.com/paper/2607.00056/) (2026)

## Abstract (arXiv)

This paper proposes a deep learning approach to a class of active sensing problems in wireless communications in which an agent sequentially interacts with an environment over a predetermined number of time frames to gather information in order to perform a sensing or actuation task for maximizing some utility function. In such an active learning setting, the agent needs to design an adaptive sensing strategy sequentially based on the observations made so far. To tackle such a challenging problem in which the dimension of historical observations increases over time, we propose to use a long short-term memory (LSTM) network to exploit the temporal correlations in the sequence of observations and to map each observation to a fixed-size state information vector. We then use a deep neural network (DNN) to map the LSTM state at each time frame to the design of the next measurement step. Finally, we employ another DNN to map the final LSTM state to the desired solution. We investigate the performance of the proposed framework for adaptive channel sensing problems in wireless communications. In particular, we consider the adaptive beamforming problem for mmWave beam alignment and the adaptive reconfigurable intelligent surface sensing problem for reflection alignment. Numerical results demonstrate that the proposed deep active sensing strategy outperforms the existing adaptive or nonadaptive sensing schemes.