paper-with-me

홈 › Papers

Improving Confidence in the Estimation of Values and Norms

2020-04-02 · Luciano Cavalcante Siebert, Rijk Mercuur, Virginia Dignum, Jeroen van den Hoven, Catholijn Jonker

Autonomous agents (AA) will increasingly be interacting with us in our daily lives. While we want the benefits attached to AAs, it is essential that their behavior is aligned with our values and norms. Hence, an AA will need to estimate the values and norms of the humans it interacts with, which is not a straightforward task when solely observing an agent's behavior. This paper analyses to what extent an AA is able to estimate the values and norms of a simulated human agent (SHA) based on its actions in the ultimatum game. We present two methods to reduce ambiguity in profiling the SHAs: one based on search space exploration and another based on counterfactual analysis. We found that both methods are able to increase the confidence in estimating human values and norms, but differ in their applicability, the latter being more efficient when the number of interactions with the agent is to be minimized. These insights are useful to improve the alignment of AAs with human values and norms.

📄 PDF Abstract BibTeX arXiv:2004.01056

Code (0)

등록된 구현이 없습니다.

Tasks

counterfactual

Similar Papers 제목 키워드 기반

Data-driven estimation of system norms via impulse response

2021-10-23 · L. V. Fiorio, C. L. Remes, L. Campestrini, Y. R. de Novaes

This paper proposes a method for estimating the norms of a system in a pure data-driven fashion based on their identified Impulse Response (IR) coefficients. The calculation of norms is briefly reviewed and the main expr…

Constrained and Regularized Quantitative Ultrasound Parameter Estimation using ADMM

2025-01-07 · Ali K. Z. Tehrani, Hassan Rivaz, Ivan M. Rosado-Mendez

Regularized estimation of quantitative ultrasound (QUS) parameters, such as attenuation and backscatter coefficients, has gained research interest. Recently, the alternating direction method of multipliers (ADMM) has bee…

parameter estimation

Value Engineering for Autonomous Agents

2023-02-17 · Nieves Montes, Nardine Osman, Carles Sierra, Marija Slavkovik

Machine Ethics (ME) is concerned with the design of Artificial Moral Agents (AMAs), i.e. autonomous agents capable of reasoning and behaving according to moral values. Previous approaches have treated values as labels as…

Ethics

ValueScope: Unveiling Implicit Norms and Values via Return Potential Model of Social Interactions

2024-07-02 · Chan Young Park, Shuyue Stella Li, Hayoung Jung, Svitlana Volkova 외

This study introduces ValueScope, a framework leveraging language models to quantify social norms and values within online communities, grounded in social science perspectives on normative structures. We employ ValueScop…

Diversity

On the Importance of Embedding Norms in Self-Supervised Learning

2025-02-13 · Andrew Draganov, Sharvaree Vadgama, Sebastian Damrich, Jan Niklas Böhm 외

Self-supervised learning (SSL) allows training data representations without a supervised signal and has become an important paradigm in machine learning. Most SSL methods employ the cosine similarity between embedding ve…

Self-Supervised Learning