Blameworthiness in Multi-Agent Settings

Authors: Meir Friedenberg, Joseph Y. Halpern525-532

AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We provide a formal definition of blameworthiness in settings where multiple agents can collaborate to avoid a negative outcome. We first provide a method for ascribing blameworthiness to groups relative to an epistemic state... We then show how we can go from an ascription of blameworthiness for groups to an ascription of blameworthiness for individuals using a standard notion from cooperative game theory, the Shapley value. ... In future work we hope to continue exploring how these notions can be formalized and applied to a wide variety of settings, especially legal settings; we hope that others will join us in considering these problems.
Researcher Affiliation Academia Meir Friedenberg Department of Computer Science Cornell University meir@cs.cornell.edu Joseph Y. Halpern Department of Computer Science Cornell University halpern@cs.cornell.edu
Pseudocode No The paper describes formal definitions and mathematical applications but does not include any pseudocode or algorithm blocks.
Open Source Code No The paper does not mention any open-source code for the methodology it describes.
Open Datasets No The paper is theoretical and uses a hypothetical illustrative example (Section 3.4) rather than experimental data or datasets. No information about public datasets is provided.
Dataset Splits No The paper is theoretical and does not conduct experiments with datasets; therefore, no information on training, validation, or test splits is provided.
Hardware Specification No The paper is theoretical and does not report on computational experiments; therefore, no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not report on computational experiments; therefore, no software dependencies with version numbers are listed.
Experiment Setup No The paper is theoretical and does not conduct computational experiments; therefore, no experimental setup details such as hyperparameters or training configurations are provided.