The lack of trust in algorithms is usually an issue when using Reinforcement Learning (RL) agents for control in real-world domains such as production plants, autonomous vehicles, or traffic-related infrastructure, partly due to the lack of verifiability of the model itself. In such scenarios, Petri nets (PNs) are often available for flowcharts or process steps, as they are versatile and standardized. In order to facilitate integration of RL models and as a step towards increasing AI trustworthiness, we propose an approach that uses PNs with three main advantages over typical RL approaches: Firstly, the agent can now easily be modeled with a combined state including both external environmental observations and agent-specific state information from a given PN. Secondly, we can enforce constraints for state-dependent actions through the inherent PN model. And lastly, we can increase trustworthiness by verifying PN properties through techniques such as model checking. We test our approach on a typical four-way intersection traffic light control setting and present our results, beating cycle-based baselines.
Using Petri Nets as an Integrated Constraint Mechanism for Reinforcement Learning Tasks
2024 IEEE Intelligent Vehicles Symposium (IV) ; 1686-1692
02.06.2024
2454150 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Controller Design of DES Petri Nets with Mixed Constraint
British Library Online Contents | 2005
|Constraint analysis of schedulability and schedulable intervals of time constraint Petri nets
British Library Online Contents | 2002
|Operating rules description using Petri nets
Tema Archiv | 2007
|Airport Traffic Simulation Using Petri Nets
Springer Verlag | 2013
|Airport Traffic Simulation Using Petri Nets
British Library Conference Proceedings | 2013
|