2023-12-02-feng23a.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
Finetuning Offline World Models in the Real World	Oral	JkFeyEC6VXV	Reinforcement Learning (RL) is notoriously data-inefficient, which makes training on a real robot difficult. While model-based RL algorithms (world models) improve data-efficiency to some extent, they still require hours or days of interaction to learn skills. Recently, offline RL has been proposed as a framework for training RL policies on pre-existing datasets without any online interaction. However, constraining an algorithm to a fixed dataset induces a state-action distribution shift between training and inference, and limits its applicability to new tasks. In this work, we seek to get the best of both worlds: we consider the problem of pretraining a world model with offline data collected on a real robot, and then finetuning the model on online data collected by planning with the learned model. To mitigate extrapolation errors during online interaction, we propose to regularize the planner at test-time by balancing estimated returns and (epistemic) model uncertainty. We evaluate our method on a variety of visuo-motor control tasks in simulation and on a real robot, and find that our method enables few-shot finetuning to seen and unseen tasks even when offline data is limited. Videos are available at https://yunhaifeng.com/FOWM	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	feng23a	0	Finetuning Offline World Models in the Real World	425	445	425-445	425	false	Feng, Yunhai and Hansen, Nicklas and Xiong, Ziyan and Rajagopalan, Chandramouli and Wang, Xiaolong	given family Yunhai Feng given family Nicklas Hansen given family Ziyan Xiong given family Chandramouli Rajagopalan given family Xiaolong Wang	2023-12-02		Proceedings of The 7th Conference on Robot Learning	229	inproceedings	date-parts 2023 12 2	https://proceedings.mlr.press/v229/feng23a/feng23a.pdf