Alizée Pace
@alizeepace.bsky.social
Gemini Post-Training @ Google DeepMind
Previously: ETH Zurich, Cambridge, CERN
alizeepace.com
Previously: ETH Zurich, Cambridge, CERN
alizeepace.com
Paper: arxiv.org/abs/2406.18450
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...
arxiv.org
April 26, 2025 at 1:15 AM
Paper: arxiv.org/abs/2406.18450
Very grateful to the organisers @claireve.bsky.social, Leif Döring, and Simon Weißmann for inviting me and putting together a fantastic event.
February 13, 2025 at 10:48 AM
Very grateful to the organisers @claireve.bsky.social, Leif Döring, and Simon Weißmann for inviting me and putting together a fantastic event.
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
Link: arxiv.org/abs/2406.18450
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...
arxiv.org
February 13, 2025 at 10:48 AM
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
Link: arxiv.org/abs/2406.18450