Large Language Models as Generalizable Policies for Embodied Tasks
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Embodied AI, Reinforcement Learning, Large Language Models, Foundational Models
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: Reinforcement Learned Policies for multi-task embodied AI problems, when initialized from LLMs, demonstrate strong generalization properties across novel task and novel ways of describing tasks.
Abstract: 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 instructions and visual egocentric observations and output actions directly in the environment. Using reinforcement learning, we train LLaRP to see and act solely through environmental interactions. We show that LLaRP is robust to complex paraphrasings of task instructions and can generalize to new tasks that require novel optimal behavior. In particular, on 1,000 unseen tasks it achieves 42% success rate, 1.7x the success rate of other common learned baselines or zero-shot applications of LLMs. Finally, to aid the community in studying language conditioned, massively multi-task, embodied AI problems we release a novel benchmark, Language Rearrangement, consisting of 150,000 training and 1,000 testing tasks for language-conditioned rearrangement.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Primary Area: applications to robotics, autonomy, planning
Submission Number: 4739
Loading