2022-06-28-blau22a.md

title	booktitle	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
Optimizing Sequential Experimental Design with Deep Reinforcement Learning	Proceedings of the 39th International Conference on Machine Learning	Bayesian approaches developed to solve the optimal design of sequential experiments are mathematically elegant but computationally challenging. Recently, techniques using amortization have been proposed to make these Bayesian approaches practical, by training a parameterized policy that proposes designs efficiently at deployment time. However, these methods may not sufficiently explore the design space, require access to a differentiable probabilistic model and can only optimize over continuous design spaces. Here, we address these limitations by showing that the problem of optimizing policies can be reduced to solving a Markov decision process (MDP). We solve the equivalent MDP with modern deep reinforcement learning techniques. Our experiments show that our approach is also computationally efficient at deployment time and exhibits state-of-the-art performance on both continuous and discrete design spaces, even when the probabilistic model is a black box.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	blau22a	0	Optimizing Sequential Experimental Design with Deep Reinforcement Learning	2107	2128	2107-2128	2107	false	Blau, Tom and Bonilla, Edwin V. and Chades, Iadine and Dezfouli, Amir	given family Tom Blau given family Edwin V. Bonilla given family Iadine Chades given family Amir Dezfouli	2022-06-28		Proceedings of the 39th International Conference on Machine Learning	162	inproceedings	date-parts 2022 6 28	https://proceedings.mlr.press/v162/blau22a/blau22a.pdf