Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Mackraz, Natalie"'
Accommodating human preferences is essential for creating AI agents that deliver personalized and effective interactions. Recent work has shown the potential for LLMs to infer preferences from user interactions, but they often produce broad and gener
Externí odkaz:
http://arxiv.org/abs/2410.06273
Preference-based reinforcement learning (PbRL) aligns a robot behavior with human preferences via a reward function learned from binary feedback over agent behaviors. We show that dynamics-aware reward functions improve the sample efficiency of PbRL
Externí odkaz:
http://arxiv.org/abs/2402.17975
Autor:
Szot, Andrew, Schwarzer, Max, Agrawal, Harsh, Mazoure, Bogdan, Talbott, Walter, Metcalf, Katherine, Mackraz, Natalie, Hjelm, Devon, Toshev, Alexander
We show that large language models (LLMs) can be adapted to be generalizable policies for embodied visual tasks. Our approach, called Large LAnguage model Reinforcement Learning Policy (LLaRP), adapts a pre-trained frozen LLM to take as input text in
Externí odkaz:
http://arxiv.org/abs/2310.17722
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.