John Aslanides — accepted AI-conference papers

2022

Fine-tuning language models to find agreement among humans with diverse preferences

Michiel A. Bakker, Martin J Chadwick, Hannah Sheahan, Michael Henry Tessler, Lucy Campbell-Gillingham, Jan Balaguer +5

NeurIPS 2022accept

Recent work in large language modeling (LLMs) has used fine-tuning to align outputs with the preferences of a prototypical user. This work assumes that human preferences are static and homogeneous across individuals, so that aligning to a single "generic" user will confer more general alignment. Her…

Cited by 258 Source ↗PDF ↗Scholar ↗

2022

Red Teaming Language Models with Language Models

Ethan Perez, Saffron Huang, Francis Song, Trevor Cai, Roman Ring, John Aslanides +3

EMNLP 2022main

Language Models (LMs) often cannot be deployed because of their potential to harm users in hard-to-predict ways. Prior work identifies harmful behaviors before deployment by using human annotators to hand-write test cases. However, human annotation is expensive, limiting the number and diversity of…

Cited by 685 Source ↗PDF ↗code ↗Scholar ↗

2020

Behaviour Suite for Reinforcement Learning

Ian Osband, Yotam Doron, Matteo Hessel, John Aslanides, Eren Sezener, Andre Saraiva +8

ICLR 2020spotlight

This paper introduces the Behaviour Suite for Reinforcement Learning, or bsuite for short. bsuite is a collection of carefully-designed experiments that investigate core capabilities of reinforcement learning (RL) agents with two objectives. First, to collect clear, informative and scalable problems…

Cited by 215 Source ↗code ↗Scholar ↗

2019

When to use parametric models in reinforcement learning?

Hado P van Hasselt, Matteo Hessel, John Aslanides

NeurIPS 2019poster

We examine the question of when and how parametric models are most useful in reinforcement learning. In particular, we look at commonalities and differences between parametric models and experience replay. Replay-based learning algorithms share important traits with model-based approaches, includi…

Cited by 243 Source ↗PDF ↗Scholar ↗

2018

Randomized Prior Functions for Deep Reinforcement Learning

Ian Osband, John Aslanides, Albin Cassirer

NeurIPS 2018spotlight

Dealing with uncertainty is essential for efficient reinforcement learning. There is a growing literature on uncertainty estimation for deep learning from fixed datasets, but many of the most popular approaches are poorly-suited to sequential decision problems. Other methods, such as bootstrap sampl…

Cited by 499 Source ↗PDF ↗Scholar ↗