# DeepRMSA: A Deep Reinforcement Learning Framework for Routing, Modulation and Spectrum Assignment in Elastic Optical Networks

arXiv: https://arxiv.org/abs/1905.02248 · HTML: https://mlsanity.com/paper/1905.02248/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 May 2019.

## Built on by (most cited first, 7 of 7)

- [MAGNNETO: A Graph Neural Network-based Multi-Agent system for Traffic Engineering](https://mlsanity.com/paper/2303.18157/) (2023)
- [Controlling chaotic itinerancy in laser dynamics for reinforcement learning](https://mlsanity.com/paper/2205.05987/) (2022)
- [Parallel photonic accelerator for decision making using optical spatiotemporal chaos](https://mlsanity.com/paper/2210.06976/) (2022)
- [Model-free reinforcement learning with noisy actions for automated experimental control in optics](https://mlsanity.com/paper/2405.15421/) (2024)
- [Resource Allocation in Multicore Elastic Optical Networks: A Deep Reinforcement Learning Approach](https://mlsanity.com/paper/2207.02074/) (2022)
- [Reinforcement Learning for Dynamic Resource Allocation in Optical Networks: Hype or Hope?](https://mlsanity.com/paper/2502.12804/) (2025)
- [Reinforcement Learning with Graph Attention for Routing and Wavelength Assignment with Lightpath Reuse](https://mlsanity.com/paper/2502.14741/) (2025)

## Abstract (arXiv)

This paper proposes DeepRMSA, a deep reinforcement learning framework for routing, modulation and spectrum assignment (RMSA) in elastic optical networks (EONs). DeepRMSA learns the correct online RMSA policies by parameterizing the policies with deep neural networks (DNNs) that can sense complex EON states. The DNNs are trained with experiences of dynamic lightpath provisioning. We first modify the asynchronous advantage actor-critic algorithm and present an episode-based training mechanism for DeepRMSA, namely, DeepRMSA-EP. DeepRMSA-EP divides the dynamic provisioning process into multiple episodes (each containing the servicing of a fixed number of lightpath requests) and performs training by the end of each episode. The optimization target of DeepRMSA-EP at each step of servicing a request is to maximize the cumulative reward within the rest of the episode. Thus, we obviate the need for estimating the rewards related to unknown future states. To overcome the instability issue in the training of DeepRMSA-EP due to the oscillations of cumulative rewards, we further propose a window-based flexible training mechanism, i.e., DeepRMSA-FLX. DeepRMSA-FLX attempts to smooth out the oscillations by defining the optimization scope at each step as a sliding window, and ensuring that the cumulative rewards always include rewards from a fixed number of requests. Evaluations with the two sample topologies show that DeepRMSA-FLX can effectively stabilize the training while achieving blocking probability reductions of more than 20.3% and 14.3%, when compared with the baselines.