2023-12-02-luo23a.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
Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning	Poster	n9lew97SAn	The offline reinforcement learning (RL) paradigm provides a general recipe to convert static behavior datasets into policies that can perform better than the policy that collected the data. While policy constraints, conservatism, and other methods for mitigating distributional shifts have made offline reinforcement learning more effective, the continuous action setting often necessitates various approximations for applying these techniques. Many of these challenges are greatly alleviated in discrete action settings, where offline RL constraints and regularizers can often be computed more precisely or even exactly. In this paper, we propose an adaptive scheme for action quantization. We use a VQ-VAE to learn state- conditioned action quantization, avoiding the exponential blowup that comes with naïve discretization of the action space. We show that several state-of-the-art offline RL methods such as IQL, CQL, and BRAC improve in performance on benchmarks when combined with our proposed discretization scheme. We further validate our approach on a set of challenging long-horizon complex robotic manipulation tasks in the Robomimic environment, where our discretized offline RL algorithms are able to improve upon their continuous counterparts by 2-3x. Our project page is at saqrl.github.io	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	luo23a	0	Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning	1348	1361	1348-1361	1348	false	Luo, Jianlan and Dong, Perry and Wu, Jeffrey and Kumar, Aviral and Geng, Xinyang and Levine, Sergey	given family Jianlan Luo given family Perry Dong given family Jeffrey Wu given family Aviral Kumar given family Xinyang Geng given family Sergey Levine	2023-12-02		Proceedings of The 7th Conference on Robot Learning	229	inproceedings	date-parts 2023 12 2	https://proceedings.mlr.press/v229/luo23a/luo23a.pdf