Using Component Abstraction for Automatic Generation of Macro-Actions
نویسندگان
چکیده
Despite major progress in AI planning over the last few years, many interesting domains remain challenging for current planners. This paper presents component abstraction, an automatic and generic technique that can reduce the complexity of an important class of planning problems. Component abstraction uses static facts in a problem definition to decompose the problem into linked abstract components. A local analysis of each component is performed to speed up planning at the component level. Our implementation uses this analysis to statically build macro operators specific to each component. A dynamic filtering process keeps for future use only the most useful macro operators. We demonstrate our ideas in Depots, Satellite, and Rovers, three standard domains used in the third AI planning competition. Our results show an impressive potential for macro operators to reduce the search complexity and achieve more stable performance.
منابع مشابه
Automatic Workflow Generation and Modification by Enterprise Ontologies and Documents
This article presents a novel method and development paradigm that proposes a general template for an enterprise information structure and allows for the automatic generation and modification of enterprise workflows. This dynamically integrated workflow development approach utilises a conceptual ontology of domain processes and tasks, enterprise charts, and enterprise entities. It also suggests...
متن کاملAutomatic Workflow Generation and Modification by Enterprise Ontologies and Documents
This article presents a novel method and development paradigm that proposes a general template for an enterprise information structure and allows for the automatic generation and modification of enterprise workflows. This dynamically integrated workflow development approach utilises a conceptual ontology of domain processes and tasks, enterprise charts, and enterprise entities. It also suggests...
متن کاملImprovement of generative adversarial networks for automatic text-to-image generation
This research is related to the use of deep learning tools and image processing technology in the automatic generation of images from text. Previous researches have used one sentence to produce images. In this research, a memory-based hierarchical model is presented that uses three different descriptions that are presented in the form of sentences to produce and improve the image. The proposed ...
متن کاملModular Code Generation from Synchronous Block Diagrams
We study modular, automatic code generation from hierarchical block diagrams with synchronous semantics. Such diagrams are the fundamental model behind widespread tools such as Simulink and SCADE. Modularity means code is generated for a given composite block independently from context, that is, without knowing in which diagrams this block is going to be used. This can be achieved by abstractin...
متن کاملPlanning with Closed-Loop Macro Actions
Planning and learning at multiple levels of tempo ral abstraction is a key problem for arti cial intelli gence In this paper we summarize an approach to this problem based on the mathematical framework of Markov decision processes and reinforcement learn ing Conventional model based reinforcement learning uses primitive actions that last one time step and that can be modeled independently of th...
متن کامل