2021-07-01-agarwal21b.md

title	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
A Regret Minimization Approach to Iterative Learning Control	We consider the setting of iterative learning control, or model-based policy learning in the presence of uncertain, time-varying dynamics. In this setting, we propose a new performance metric, planning regret, which replaces the standard stochastic uncertainty assumptions with worst case regret. Based on recent advances in non-stochastic control, we design a new iterative algorithm for minimizing planning regret that is more robust to model mismatch and uncertainty. We provide theoretical and empirical evidence that the proposed algorithm outperforms existing methods on several benchmarks.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	agarwal21b	0	A Regret Minimization Approach to Iterative Learning Control	100	109	100-109	100	false	Agarwal, Naman and Hazan, Elad and Majumdar, Anirudha and Singh, Karan	given family Naman Agarwal given family Elad Hazan given family Anirudha Majumdar given family Karan Singh	2021-07-01		Proceedings of the 38th International Conference on Machine Learning	139	inproceedings	date-parts 2021 7 1	http://proceedings.mlr.press/v139/agarwal21b/agarwal21b.pdf	label link Supplementary PDF http://proceedings.mlr.press/v139/agarwal21b/agarwal21b-supp.pdf