2023-12-02-mirchandani23a.md

title	section	openreview	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Large Language Models as General Pattern Machines	Poster	RcZMI8MSyE	We observe that pre-trained large language models (LLMs) are capable of autoregressively completing complex token sequences–from arbitrary ones procedurally generated by probabilistic context-free grammars (PCFG), to more rich spatial patterns found in the Abstraction and Reasoning Corpus (ARC), a general AI benchmark, prompted in the style of ASCII art. Surprisingly, pattern completion proficiency can be partially retained even when the sequences are expressed using tokens randomly sampled from the vocabulary. These results suggest that without any additional training, LLMs can serve as general sequence modelers, driven by in-context learning. In this work, we investigate how these zero-shot capabilities may be applied to problems in robotics–from extrapolating sequences of numbers that represent states over time to complete simple motions, to least-to-most prompting of reward-conditioned trajectories that can discover and represent closed-loop policies (e.g., a stabilizing controller for CartPole). While difficult to deploy today for real systems due to latency, context size limitations, and compute costs, the approach of using LLMs to drive low-level control may provide an exciting glimpse into how the patterns among words could be transferred to actions.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	mirchandani23a	0	Large Language Models as General Pattern Machines	2498	2518	2498-2518	2498	false	Mirchandani, Suvir and Xia, Fei and Florence, Pete and Ichter, Brian and Driess, Danny and Arenas, Montserrat Gonzalez and Rao, Kanishka and Sadigh, Dorsa and Zeng, Andy	given family Suvir Mirchandani given family Fei Xia given family Pete Florence given family Brian Ichter given family Danny Driess given family Montserrat Gonzalez Arenas given family Kanishka Rao given family Dorsa Sadigh given family Andy Zeng	2023-12-02		Proceedings of The 7th Conference on Robot Learning	229	inproceedings	date-parts 2023 12 2	https://proceedings.mlr.press/v229/mirchandani23a/mirchandani23a.pdf