Search Results for author: Alizée Pace

Found 6 papers, 2 papers with code

Preference Elicitation for Offline Reinforcement Learning

no code implementations26 Jun 2024 Alizée Pace, Bernhard Schölkopf, Gunnar Rätsch, Giorgia Ramponi

Drawing on insights from both the offline RL and the preference-based RL literature, our algorithm employs a pessimistic approach for out-of-distribution data, and an optimistic approach for acquiring informative preferences about the optimal policy.

Offline RL reinforcement-learning +1

West-of-N: Synthetic Preference Generation for Improved Reward Modeling

1 code implementation22 Jan 2024 Alizée Pace, Jonathan Mallinson, Eric Malmi, Sebastian Krause, Aliaksei Severyn

The success of reinforcement learning from human feedback (RLHF) in language model alignment is strongly dependent on the quality of the underlying reward model.

Language Modelling

On the Importance of Step-wise Embeddings for Heterogeneous Clinical Time-Series

no code implementations15 Nov 2023 Rita Kuznetsova, Alizée Pace, Manuel Burger, Hugo Yèche, Gunnar Rätsch

Recent findings in deep learning for tabular data are now surpassing these classical methods by better handling the severe heterogeneity of data input features.

Time Series

Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding

no code implementations1 Jun 2023 Alizée Pace, Hugo Yèche, Bernhard Schölkopf, Gunnar Rätsch, Guy Tennenholtz

A prominent challenge of offline reinforcement learning (RL) is the issue of hidden confounding: unobserved variables may influence both the actions taken by the agent and the observed outcomes.

Management Offline RL +2

Temporal Label Smoothing for Early Event Prediction

1 code implementation29 Aug 2022 Hugo Yèche, Alizée Pace, Gunnar Rätsch, Rita Kuznetsova

TLS reduces the number of missed events by up to a factor of two over previously used approaches in early event prediction.

Binary Classification Circulatory Failure +3

POETREE: Interpretable Policy Learning with Adaptive Decision Trees

no code implementations ICLR 2022 Alizée Pace, Alex J. Chan, Mihaela van der Schaar

Building models of human decision-making from observed behaviour is critical to better understand, diagnose and support real-world policies such as clinical care.

Decision Making

Cannot find the paper you are looking for? You can Submit a new open access paper.