2023-12-02-chen23c.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
PlayFusion: Skill Acquisition via Diffusion from Language-Annotated Play	Poster	afF8RGcBBP	Learning from unstructured and uncurated data has become the dominant paradigm for generative approaches in language or vision. Such unstructured and unguided behavior data, commonly known as play, is also easier to collect in robotics but much more difficult to learn from due to its inherently multimodal, noisy, and suboptimal nature. In this paper, we study this problem of learning goal-directed skill policies from unstructured play data which is labeled with language in hindsight. Specifically, we leverage advances in diffusion models to learn a multi-task diffusion model to extract robotic skills from play data. Using a conditional denoising diffusion process in the space of states and actions, we can gracefully handle the complexity and multimodality of play data and generate diverse and interesting robot behaviors. To make diffusion models more useful for skill learning, we encourage robotic agents to acquire a vocabulary of skills by introducing discrete bottlenecks into the conditional behavior generation process. In our experiments, we demonstrate the effectiveness of our approach across a wide variety of environments in both simulation and the real world. Video results available at https://play-fusion.github.io.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	chen23c	0	PlayFusion: Skill Acquisition via Diffusion from Language-Annotated Play	2012	2029	2012-2029	2012	false	Chen, Lili and Bahl, Shikhar and Pathak, Deepak	given family Lili Chen given family Shikhar Bahl given family Deepak Pathak	2023-12-02		Proceedings of The 7th Conference on Robot Learning	229	inproceedings	date-parts 2023 12 2	https://proceedings.mlr.press/v229/chen23c/chen23c.pdf