Learning Task Decomposition with Ordered Memory Policy Network
Many complex real-world tasks are composed of several levels of sub-tasks. Humans leverage these hierarchical structures to accelerate the learning process and achieve better generalization. In this work, we study the inductive bias and propose Ordered Memory Policy Network (OMPN) to discover subtask hierarchy by learning from demonstration. The discovered subtask hierarchy could be used to perform task decomposition, recovering the subtask boundaries in an unstruc-tured demonstration. Experiments on Craft and Dial demonstrate that our modelcan achieve higher task decomposition performance under both unsupervised and weakly supervised settings, comparing with strong baselines. OMPN can also bedirectly applied to partially observable environments and still achieve higher task decomposition performance. Our visualization further confirms that the subtask hierarchy can emerge in our model.
Code (0)
등록된 구현이 없습니다.
Tasks
Inductive BiasSimilar Papers 제목 키워드 기반
Learning Task Decomposition with Order-Memory Policy Network
Many complex real-world tasks are composed of several levels of sub-tasks. Humans leverage these hierarchical structures to accelerate the learning process and achieve better generalization. To simulate this process, we …
Imitation LearningInductive BiasTotally and Partially Ordered Hierarchical Planners in PDDL4J Library
In this paper, we outline the implementation of the TFD (Totally Ordered Fast Downward) and the PFD (Partially ordered Fast Downward) hierarchical planners that participated in the first HTN IPC competition in 2020. Thes…
Axis-Aligned Semantics for ODRL: Resolving Dimensional Ambiguity in Policy Constraints
The Open Digital Rights Language (ODRL) represents policy constraints as triples of a left operand, an operator, and a value. Several spatial operands, however, range over multi-axis domains such as width, height, and de…
PODiff: Latent Diffusion in Proper Orthogonal Decomposition Space for Scientific Super-Resolution
Probabilistic super-resolution of high-dimensional spatial fields using diffusion models is often computationally prohibitive due to the cost of operating directly in pixel space. We propose PODiff, a structured conditio…
LLM-based policy generation for intent-based management of applications
Automated management requires decomposing high-level user requests, such as intents, to an abstraction that the system can understand and execute. This is challenging because even a simple intent requires performing a nu…
Management