2024-09-12-cheng24a.md

title	abstract	openreview	section	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
SMuCo: Reinforcement Learning for Visual Control via Sequential Multi-view Total Correlation	The advent of abundant image data has catalyzed the advancement of visual control in reinforcement learning (RL) systems, leveraging multiple view- points to capture the same physical states, which could enhance control performance theoretically. However, integrating multi-view data into representation learning remains challenging. In this paper, we introduce SMuCo, an innovative multi-view reinforcement learning algorithm that constructs robust latent representations by optimizing multi- view sequential total correlation. This technique effectively captures task-relevant information and temporal dynamics while filtering out irrelevant data. Our method supports an unlimited number of views and demonstrates superior performance over leading model-free and model-based RL algorithms. Empirical results from the DeepMind Control Suite and the Sapien Basic Manipulation Task confirm SMuCo’s enhanced efficacy, significantly improving task performance across diverse scenarios and views.	Eg5AmHPQKe	Papers	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	cheng24a	0	SMuCo: Reinforcement Learning for Visual Control via Sequential Multi-view Total Correlation	698	717	698-717	698	false	Cheng, Tong and Dong, Hang and Wang, Lu and Qiao, Bo and Lin, Qingwei and Rajmohan, Saravan and Moscibroda, Thomas	given family Tong Cheng given family Hang Dong given family Lu Wang given family Bo Qiao given family Qingwei Lin given family Saravan Rajmohan given family Thomas Moscibroda	2024-09-12		Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence	244	inproceedings	date-parts 2024 9 12	https://raw.githubusercontent.com/mlresearch/v244/main/assets/cheng24a/cheng24a.pdf