ROSETTA: Constructing Code-Based Reward from Unconstrained Language Preference

Sanjana Srivastava, Kangrui Wang, Yung-Chieh Chan, Tianyuan Dai, Manling Li, Ruohan Zhang, Mengdi Xu, Jiajun Wu, Li Fei-Fei

Keywords: reward generation, LLMs for robotics, human evaluation

TL;DR: We aim to use LLMs to generate reward from unconstrained language with changing goals; this requires structure and domain knowledge in prompting, and rigorous human evaluation.

Abstract: Intelligent embodied agents not only need to accomplish preset tasks, but also learn to align with individual human needs and preferences. Extracting reward signals from human language preferences allows an embodied agent to adapt through reinforcement learning. However, human language preferences are unconstrained, diverse, and dynamic, making constructing learnable reward from them a major challenge. We present ROSETTA, a framework that uses foundation models to ground and disambiguate unconstrained natural language preference, construct multi-stage reward functions, and implement them with code generation. Unlike prior works requiring extensive offline training to get general reward models or fine-grained correction on a single task, ROSETTA allows agents to adapt online to preference that evolves and is diverse in language and content. We test ROSETTA on both short-horizon and long-horizon manipulation tasks and conduct extensive human evaluation, finding that ROSETTA outperforms SOTA baselines and achieves 87% average success rate and 86% human satisfaction across 116 preferences.

Primary Area: applications to robotics, autonomy, planning

Submission Number: 15476