EduGym: An Environment Suite for Reinforcement Learning Education

1 code implementation • 17 Nov 2023 • Thomas M. Moerland, Matthias Müller-Brockhausen, Zhao Yang, Andrius Bernatavicius, Koen Ponse, Tom Kouwenhoven, Andreas Sauter, Michiel van der Meer, Bram Renting, Aske Plaat

To solve this issue we introduce EduGym, a set of educational reinforcement learning environments and associated interactive notebooks tailored for education.

reinforcement-learning

Do Differences in Values Influence Disagreements in Online Discussions?

1 code implementation • 24 Oct 2023 • Michiel van der Meer, Piek Vossen, Catholijn M. Jonker, Pradeep K. Murukannaiah

We investigate a hypothesis that differences in personal values are indicative of disagreement in online discussions.

Leveraging Few-Shot Data Augmentation and Waterfall Prompting for Response Generation

no code implementations • 2 Aug 2023 • Lea Krause, Selene Báez Santamaría, Michiel van der Meer, Urja Khurana

This paper discusses our approaches for task-oriented conversational modelling using subjective knowledge, with a particular emphasis on response generation.

Data Augmentation Few-Shot Learning +1

Will It Blend? Mixing Training Paradigms & Prompting for Argument Quality Prediction

no code implementations • ArgMining (ACL) 2022 • Michiel van der Meer, Myrthe Reuver, Urja Khurana, Lea Krause, Selene Báez Santamaría

This paper describes our contributions to the Shared Task of the 9th Workshop on Argument Mining (2022).

Argument Mining Contrastive Learning +2

Interactive Grounded Language Understanding in a Collaborative Environment: IGLU 2021

no code implementations • 5 May 2022 • Julia Kiseleva, Ziming Li, Mohammad Aliannejadi, Shrestha Mohanty, Maartje ter Hoeve, Mikhail Burtsev, Alexey Skrynnik, Artem Zholus, Aleksandr Panov, Kavya Srinet, Arthur Szlam, Yuxuan Sun, Marc-Alexandre Côté, Katja Hofmann, Ahmed Awadallah, Linar Abdrazakov, Igor Churin, Putra Manggala, Kata Naszadi, Michiel van der Meer, Taewoon Kim

The primary goal of the competition is to approach the problem of how to build interactive agents that learn to solve a task while provided with grounded natural language instructions in a collaborative environment.

Reason Against the Machine: Future Directions for Mass Online Deliberation

no code implementations • 27 Jul 2021 • Ruth Shortall, Anatol Itten, Michiel van der Meer, Pradeep K. Murukannaiah, Catholijn M. Jonker

Designers of online deliberative platforms aim to counter the degrading quality of online debates.

Exploiting Language Instructions for Interpretable and Compositional Reinforcement Learning

no code implementations • 13 Jan 2020 • Michiel van der Meer, Matteo Pirotta, Elia Bruni

In this work, we present an alternative approach to making an agent compositional through the use of a diagnostic classifier.

Classification General Classification +2