8 papers · 1 filter
COOL-MC: Verifying and Explaining RL Policies for Multi-bridge Network Maintenance
Dennis Gross
Aging bridge networks require proactive, verifiable, and interpretable maintenance strategies, yet reinforcement learning (RL) policies trained solely on reward signals provide no…
COOL-MC: Verifying and Explaining RL Policies for Platelet Inventory Management
Dennis Gross
Platelets expire within five days. Blood banks face uncertain daily demand and must balance ordering decisions between costly wastage from overstocking and life-threatening shortag…
Translating the Rashomon Effect to Sequential Decision-Making Tasks
Dennis Gross, Jørn Eirik Betten, Helge Spieker
The Rashomon effect describes the phenomenon where multiple models trained on the same data produce identical predictions while differing in which features they rely on internally.…
Verifying Memoryless Sequential Decision-making of Large Language Models
Dennis Gross, Helge Spieker, Arnaud Gotlieb
We introduce a tool for rigorous and automated verification of large language model (LLM)- based policies in memoryless sequential decision-making tasks. Given a Markov decision pr…
Bounded PCTL Model Checking of Large Language Model Outputs
Dennis Gross, Helge Spieker, Arnaud Gotlieb
In this paper, we introduce LLMCHECKER, a model-checking-based verification method to verify the probabilistic computation tree logic (PCTL) properties of an LLM text generation pr…
Co-Activation Graph Analysis of Safety-Verified and Explainable Deep Reinforcement Learning Policies
Dennis Gross, Helge Spieker
Deep reinforcement learning (RL) policies can demonstrate unsafe behaviors and are challenging to interpret. To address these challenges, we combine RL policy model checking--a tec…