# Intelligent Radio Resource Slicing for 6G In-Body Subnetworks

arXiv: https://arxiv.org/abs/2603.28529 · HTML: https://mlsanity.com/paper/2603.28529/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 6 of its 24 references that are in the map.
- First posted on arXiv 30 Mar 2026.

## Placed in

- Deep reinforcement learning methods / [RL for energy, networks and operations](https://mlsanity.com/deeprl/rl-for-energy-networks-and-operations/)

## Builds on (most cited first, 6 of 6)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [ColO-RAN: Developing Machine Learning-based xApps for Open RAN Closed-loop Control on Programmable Experimental Platforms](https://mlsanity.com/paper/2112.09559/) (2021)
- [5G Wireless Network Slicing for eMBB, URLLC, and mMTC: A Communication-Theoretic View](https://mlsanity.com/paper/1804.05057/) (2018)
- [Standardization of Extended Reality (XR) over 5G and 5G-Advanced 3GPP New Radio](https://mlsanity.com/paper/2203.02242/) (2022)
- [Goal-Oriented Interference Coordination in 6G In-Factory Subnetworks](https://mlsanity.com/paper/2503.02521/) (2025)
- [Proactive Radio Resource Allocation for 6G In-Factory Subnetworks](https://mlsanity.com/paper/2504.14718/) (2025)

## Abstract (arXiv)

6G In-body Subnetworks (IBSs) represent a key enabler for supporting standalone eXtended Reality (XR) applications. IBSs are expected to operate as an underlay to existing cellular networks, giving rise to coexistence challenges when sharing radio resources with other cellular users, such as enhanced Mobile Broadband (eMBB) users. Such resource allocation problem is highly dynamic and inherently non-convex due to heterogeneous service demands and fluctuating channel conditions. In this paper, we propose an intelligent radio resource slicing strategy based on the Soft Actor-Critic (SAC) deep reinforcement learning algorithm. The proposed SAC-based slicing method addresses the coexistence challenge between IBSs and eMBB users by optimizing a refined reward function that explicitly incorporates XR cross-modal delay alignment to ensure immersive experience while preserving eMBB service guarantees. Extensive system-level simulations are performed under realistic network conditions and the results demonstrate that the proposed method can enhance user experience by 12-85% under different network densities compared to baseline methods while maintaining the target data rate for eMBB users.