2023-07-02-dadvar23a.md

abstract	openreview	title	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
In many real-world problems, the learning agent needs to learn a problem’s abstractions and solution simultaneously. However, most such abstractions need to be designed and refined by hand for different problems and domains of application. This paper presents a novel top-down approach for constructing state abstractions while carrying out reinforcement learning (RL). Starting with state variables and a simulator, it presents a novel domain-independent approach for dynamically computing an abstraction based on the dispersion of temporal difference errors in abstract states as the agent continues acting and learning. Extensive empirical evaluation on multiple domains and problems shows that this approach automatically learns semantically rich abstractions that are finely-tuned to the problem, yield strong sample efficiency, and result in the RL agent significantly outperforming existing approaches.	Z8_-LjXPKNe	Conditional abstraction trees for sample-efficient reinforcement learning	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	dadvar23a	0	Conditional abstraction trees for sample-efficient reinforcement learning	485	495	485-495	485	false	Dadvar, Mehdi and Nayyar, Rashmeet Kaur and Srivastava, Siddharth	given family Mehdi Dadvar given family Rashmeet Kaur Nayyar given family Siddharth Srivastava	2023-07-02		Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence	216	inproceedings	date-parts 2023 7 2	https://proceedings.mlr.press/v216/dadvar23a/dadvar23a.pdf	label link Supplementary PDF https://proceedings.mlr.press/v216/dadvar23a/dadvar23a-supp.pdf