Catholijn M. Jonker

Learning Multimodal Transition Dynamics for Model-Based Reinforcement Learning

2017 · Data Archiving and Networked Services (DANS)

In this paper we study how to learn stochastic, multimodal transition dynamics in reinforcement learning (RL) tasks. We focus on evaluating transition function estimation, while we defer planning over this model to future work. Stochasticity …

An Empirical Analysis of Diversity in Argument Summarization

2024 · VU Research Portal

Presenting high-level arguments is a crucial task for fostering participation in online societal discussions. Current argument summarization approaches miss an important facet of this task -- capturing diversity -- which is important for accommodating multiple …

Value Preferences Estimation and Disambiguation in Hybrid Participatory Systems

2024 · arXiv (Cornell University)

Understanding citizens' values in participatory systems is crucial for citizen-centric policy-making. We envision a hybrid participatory system where participants make choices and provide motivations for those choices, and AI agents estimate their value preferences by …

Will Annotators Disagree? Identifying Subjectivity in Value-Laden Arguments

2025 · arXiv (Cornell University)

Aggregating multiple annotations into a single ground truth label may hide valuable insights into annotator disagreement, particularly in tasks where subjectivity plays a crucial role. In this work, we explore methods for identifying subjectivity in …