2023-04-11-bennett23a.md

title	software	abstract	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
Provable Safe Reinforcement Learning with Binary Feedback	https://github.com/CausalML/SABRE	Safety is a crucial necessity in many applications of reinforcement learning (RL), whether robotic, automotive, or medical. Many existing approaches to safe RL rely on receiving numeric safety feedback, but in many cases this feedback can only take binary values; that is, whether an action in a given state is safe or unsafe. This is particularly true when feedback comes from human experts. We therefore consider the problem of provable safe RL when given access to an offline oracle providing binary feedback on the safety of state, action pairs. We provide a novel meta algorithm, SABRE, which can be applied to any MDP setting given access to a blackbox PAC RL algorithm for that setting. SABRE applies concepts from active learning to reinforcement learning to provably control the number of queries to the safety oracle. SABRE works by iteratively exploring the state space to find regions where the agent is currently uncertain about safety. Our main theoretical results shows that, under appropriate technical assumptions, SABRE never takes unsafe actions during training, and is guaranteed to return a near-optimal safe policy with high probability. We provide a discussion of how our meta-algorithm may be applied to various settings studied in both theoretical and empirical frameworks.	Regular Papers	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	bennett23a	0	Provable Safe Reinforcement Learning with Binary Feedback	10871	10900	10871-10900	10871	false	Bennett, Andrew and Misra, Dipendra and Kallus, Nathan	given family Andrew Bennett given family Dipendra Misra given family Nathan Kallus	2023-04-11		Proceedings of The 26th International Conference on Artificial Intelligence and Statistics	206	inproceedings	date-parts 2023 4 11	https://proceedings.mlr.press/v206/bennett23a/bennett23a.pdf