Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Formal Quality Measures for Predictors in Markov Decision Processes
Authors: Christel Baier, Sascha Klüppelholz, Jakob Piribauer, Robin Ziemek
AAAI 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | Main contributions are the introduction of quantitative notions that measure the effectiveness of predictors in terms of their average capability to predict the occurrence of failures or other undesired system behaviors. The average is taken over all memoryless policies. We study two classes of such notions. One class is inspired by concepts that have been introduced in statistical analysis... Second, we study a measure that borrows ideas from recent work on probability-raising causality in MDPs... We then address the complexity of deciding the existence of PR policies (Sec. 4.2). |
| Researcher Affiliation | Academia | Chistel Baier1, Sascha Kl uppelholz1 Jakob Piribauer1,2, Robin Ziemek1 * 1Technische Universit at Dresden 2Universit at Leipzig EMAIL |
| Pseudocode | No | The paper describes methods mathematically and textually, without presenting any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain any statements about releasing code or links to code repositories for the described methodology. |
| Open Datasets | No | The paper uses illustrative conceptual examples (e.g., a communication network in Figure 2) rather than real or specific publicly available datasets for its analysis. |
| Dataset Splits | No | Since the paper is theoretical and does not conduct experiments on datasets, it does not provide information about dataset splits. |
| Hardware Specification | No | The paper is theoretical and focuses on formal measures and complexity analysis; it does not describe experimental work requiring specific hardware. |
| Software Dependencies | No | The paper is theoretical and does not detail an implementation or list specific software dependencies with version numbers for reproducing experimental results. Mentions of solvers like CPLEX are in the context of general optimization problems, not specific to their implementation. |
| Experiment Setup | No | The paper is theoretical and focuses on formal analysis; it does not describe experimental setups, hyperparameters, or training configurations. |