Alizée Pace

Preference Elicitation for Offline Reinforcement Learning Applying reinforcement learning (RL) to real-world problems is often made challenging by the inability to interact with the environment and the difficulty of designing reward functions. Offline RL add...

Paper: arxiv.org/abs/2406.18450

RL for real-world applications = offline learning + reward learning. How do we make this work?

Find out more at ICLR poster #377 at 10am today!

@gioramponi.bsky.social and I will be presenting our latest work on offline preference-based RL (joint w/ @gxxxr.bsky.social and Bernhard Schölkopf).

🎉 Yesterday, @alizeepace.bsky.social, our first PhD Fellow of the @eth-ai-center.bsky.social, graduated! She was supervised by ETH AI Center Faculty members Prof. Rätsch @gxxxr.bsky.social and Prof. Schölkopf. Congrats, Dr. Pace! Next, she will join Google DeepMind in Zurich as a Research Scientist.

Very grateful to the organisers @claireve.bsky.social, Leif Döring, and Simon Weißmann for inviting me and putting together a fantastic event.

Preference Elicitation for Offline Reinforcement Learning Applying reinforcement learning (RL) to real-world problems is often made challenging by the inability to interact with the environment and the difficulty of designing reward functions. Offline RL...

This is joint work with Bernhard Schölkopf, @gxxxr.bsky.social, and @gioramponi.bsky.social, which we will also be presenting at ICLR 2025 🎉
Link: arxiv.org/abs/2406.18450

Last Friday, I had the pleasure of giving an invited talk at the workshop on Reinforcement Learning in Mannheim, Germany!

I presented recent work on offline preference-based reinforcement learning, aiming to make RL more practical for real-world applications like healthcare.

Machine learning has made incredible breakthroughs, but our theoretical understanding lags behind.

We take a step towards unravelling its mystery by explaining why the phenomenon of disentanglement arises in generative latent variable models.

Blog post: carl-allen.github.io/theory/2024/...