# Introducing PetriRL: An Innovative Framework for JSSP Resolution Integrating Petri nets and Event-based Reinforcement Learning

arXiv: https://arxiv.org/abs/2402.00046 · HTML: https://mlsanity.com/paper/2402.00046/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 9 of its 45 references that are in the map.
- First posted on arXiv 23 Jan 2024.

## 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, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Overcoming Exploration in Reinforcement Learning with Demonstrations](https://mlsanity.com/paper/1709.10089/) (2017)
- [A Closer Look at Invalid Action Masking in Policy Gradient Algorithms](https://mlsanity.com/paper/2006.14171/) (2020)
- [Mastering Complex Control in MOBA Games with Deep Reinforcement Learning](https://mlsanity.com/paper/1912.09729/) (2019)
- [Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning](https://mlsanity.com/paper/2010.12367/) (2020)
- [Learning to schedule job-shop problems: Representation and policy learning using graph neural network and reinforcement learning](https://mlsanity.com/paper/2106.01086/) (2021)
- [Deep Reinforcement Learning for Event-Triggered Control](https://mlsanity.com/paper/1809.05152/) (2018)
- [Graph neural networks-based Scheduler for Production planning problems using Reinforcement Learning](https://mlsanity.com/paper/2009.03836/) (2020)

## Built on by (most cited first, 6 of 6)

- [Graph Neural Networks for Job Shop Scheduling Problems: A Survey](https://mlsanity.com/paper/2406.14096/) (2024)
- [Flexible Manufacturing Systems Intralogistics: Dynamic Optimization of AGVs and Tool Sharing Using Coloured-Timed Petri Nets and Actor-Critic RL with Actions Masking](https://mlsanity.com/paper/2601.04887/) (2026)
- [Predicting Wall Thickness Changes in Cold Forging Processes: An Integrated FEM and Neural Network approach](https://mlsanity.com/paper/2411.13366/) (2024)
- [GymPN: A Library for Decision-Making in Process Management Systems](https://mlsanity.com/paper/2506.20404/) (2025)
- [Process mining-driven modeling and simulation to enhance fault diagnosis in cyber-physical systems](https://mlsanity.com/paper/2506.21502/) (2025)
- [Policy-Based Reinforcement Learning with Action Masking for Dynamic Job Shop Scheduling under Uncertainty: Handling Random Arrivals and Machine Failures](https://mlsanity.com/paper/2601.09293/) (2026)

## Abstract (arXiv)

Resource utilization and production process optimization are crucial for companies in today's competitive industrial landscape. Addressing the complexities of job shop scheduling problems (JSSP) is essential to improving productivity, reducing costs, and ensuring timely delivery. We propose PetriRL, a novel framework integrating Petri nets and deep reinforcement learning (DRL) for JSSP optimization. PetriRL capitalizes on the inherent strengths of Petri nets in modelling discrete event systems while leveraging the advantages of a graph structure. The Petri net governs automated components of the process, ensuring adherence to JSSP constraints. This allows for synergistic collaboration with optimization algorithms such as DRL, particularly in critical decision-making. Unlike traditional methods, PetriRL eliminates the need to preprocess JSSP instances into disjunctive graphs and enhances the explainability of process status through its graphical structure based on places and transitions. Additionally, the inherent graph structure of Petri nets enables the dynamic additions of job operations during the inference phase without requiring agent retraining, thus enhancing flexibility. Experimental results demonstrate PetriRL's robust generalization across various instance sizes and its competitive performance on public test benchmarks and randomly generated instances. Results are compared to a wide range of optimization solutions such as heuristics, metaheuristics, and learning-based algorithms. Finally, the added values of the framework's key elements, such as event-based control and action masking, are studied in the ablation study.