EU Horizon 2020
Horizon 2020
HomeNewsResearch ThemesPeopleKey Prior PublicationsPublications
[YSN+24b] Rui Yan, Gabriel Santos, Gethin Norman, David Parker, Marta Kwiatkowska. Partially Observable Stochastic Games with Neural Perception Mechanisms. In Proc. 26th International Symposium on Formal Methods (FM'24), Springer. To appear. 2024. [pdf] [bib]
Downloads:  pdf pdf (7.22 MB)  bib bib
Notes: An extended version of this paper can be found at https://arxiv.org/abs/2310.11566. The original publication is available at link.springer.com.
Abstract. Stochastic games are a well established model for multi-agent sequential decision making under uncertainty. In practical applications, though, agents often have only partial observability of their environment. Furthermore, agents increasingly perceive their environment using data-driven approaches such as neural networks trained on continuous data. We propose the model of neuro-symbolic partially-observable stochastic games (NS-POSGs), a variant of continuous-space concurrent stochastic games that explicitly incorporates neural perception mechanisms. We focus on a one-sided setting with a partially-informed agent using discrete, data-driven observations and another, fully-informed agent. We present a new method, called one-sided NS-HSVI, for approximate solution of one-sided NS-POSGs, which exploits the piecewise constant structure of the model. Using neural network pre-image analysis to construct finite polyhedral representations and particle-based representations for beliefs, we implement our approach and illustrate its practical applicability to the analysis of pedestrian-vehicle and pursuit-evasion scenarios.