website/content/paper/2403.01.md

draft	title	authors	date	publish_date	conference	isbn	doi	volume	firstpage	lastpage	language	pdf_url	abstract
false	Partially Observable Hierarchical Reinforcement Learning with AI Planning (Student Abstract)	Brandon Rozek Junkyu Lee Harsha Kokel Michael Katz Shirin Sohrabi	2024-03-24	2024/03/24	AAAI Conference on Artificial Intelligence		10.1609/aaai.v38i21.30504	38	23635	23636	English	https://ojs.aaai.org/index.php/AAAI/article/view/30504/32640	Partially observable Markov decision processes (POMDPs) challenge reinforcement learning agents due to incomplete knowledge of the environment. Even assuming monotonicity in uncertainty, it is difficult for an agent to know how and when to stop exploring for a given task. In this abstract, we discuss how to use hierarchical reinforcement learning (HRL) and AI Planning (AIP) to improve exploration when the agent knows possible valuations of unknown predicates and how to discover them. By encoding the uncertainty in an abstract planning model, the agent can derive a high-level plan which is then used to decompose the overall POMDP into a tree of semi-POMDPs for training. We evaluate our agent's performance on the MiniGrid domain and show how guided exploration may improve agent performance.