# Model-free Reinforcement Learning of Semantic Communication by Stochastic Policy Gradient

arXiv: https://arxiv.org/abs/2305.03571 · HTML: https://mlsanity.com/paper/2305.03571/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 15 references that are in the map.
- First posted on arXiv 5 May 2023.

## Builds on (most cited first, 9 of 9)

- [Deep Learning Enabled Semantic Communication Systems](https://mlsanity.com/paper/2006.10685/) (2020)
- [An Introduction to Deep Learning for the Physical Layer](https://mlsanity.com/paper/1702.00832/) (2017)
- [Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications](https://mlsanity.com/paper/2207.09353/) (2022)
- [6G Networks: Beyond Shannon Towards Semantic and Goal-Oriented Communications](https://mlsanity.com/paper/2011.14844/) (2020)
- [Model-free Training of End-to-end Communication Systems](https://mlsanity.com/paper/1812.05929/) (2018)
- [A Brief Introduction to Machine Learning for Engineers](https://mlsanity.com/paper/1709.02840/) (2017)
- [Reinforcement Learning-powered Semantic Communication via Semantic Similarity](https://mlsanity.com/paper/2108.12121/) (2021)
- [Semantic Information Recovery in Wireless Networks](https://mlsanity.com/paper/2204.13366/) (2022)
- [CMDNet: Learning a Probabilistic Relaxation of Discrete Variables for Soft Detection with Low Complexity](https://mlsanity.com/paper/2102.12756/) (2021)

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

- [Semantic Communication for Cooperative Multi-Task Processing over Wireless Networks](https://mlsanity.com/paper/2404.08483/) (2024)
- [Integrating Semantic Communication and Human Decision-Making into an End-to-End Sensing-Decision Framework](https://mlsanity.com/paper/2412.05103/) (2024)

## Abstract (arXiv)

Following the recent success of Machine Learning tools in wireless communications, the idea of semantic communication by Weaver from 1949 has gained attention. It breaks with Shannon's classic design paradigm by aiming to transmit the meaning, i.e., semantics, of a message instead of its exact version, allowing for information rate savings. In this work, we apply the Stochastic Policy Gradient (SPG) to design a semantic communication system by reinforcement learning, separating transmitter and receiver, and not requiring a known or differentiable channel model -- a crucial step towards deployment in practice. Further, we derive the use of SPG for both classic and semantic communication from the maximization of the mutual information between received and target variables. Numerical results show that our approach achieves comparable performance to a model-aware approach based on the reparametrization trick, albeit with a decreased convergence rate.