A review of machine learning for automated planning
Recent discoveries in automated planning are broadening the scope of planners, from toy
problems to real applications. However, applying automated planners to real-world …
problems to real applications. However, applying automated planners to real-world …
Grammar prompting for domain-specific language generation with large language models
Large language models (LLMs) can learn to perform a wide range of natural language tasks
from just a handful of in-context examples. However, for generating strings from highly …
from just a handful of in-context examples. However, for generating strings from highly …
A review of generalized planning
S Jiménez, J Segovia-Aguas… - The Knowledge …, 2019 - cambridge.org
Generalized planning studies the representation, computation and evaluation of solutions
that are valid for multiple planning instances. These are topics studied since the early days …
that are valid for multiple planning instances. These are topics studied since the early days …
Robot task planning using semantic maps
Task planning for mobile robots usually relies solely on spatial information and on shallow
domain knowledge, such as labels attached to objects and places. Although spatial …
domain knowledge, such as labels attached to objects and places. Although spatial …
Marvin: A heuristic search planner with online macro-action learning
AI Coles, AJ Smith - Journal of Artificial Intelligence Research, 2007 - jair.org
This paper describes Marvin, a planner that competed in the Fourth International Planning
Competition (IPC 4). Marvin uses action-sequence-memoisation techniques to generate …
Competition (IPC 4). Marvin uses action-sequence-memoisation techniques to generate …
Lifted successor generation using query optimization techniques
The standard PDDL language for classical planning uses several first-order features, such
as schematic actions. Yet, most classical planners ground this first-order representation into …
as schematic actions. Yet, most classical planners ground this first-order representation into …
[PDF][PDF] Learning Control Knowledge for Forward Search Planning.
A number of today's state-of-the-art planners are based on forward state-space search. The
impressive performance can be attributed to progress in computing domain independent …
impressive performance can be attributed to progress in computing domain independent …
[PDF][PDF] Learning Macro-Actions for Arbitrary Planners and Domains.
Many complex domains and even larger problems in simple domains remain challenging in
spite of the recent progress in planning. Besides developing and improving planning …
spite of the recent progress in planning. Besides developing and improving planning …
[HTML][HTML] Learning hierarchical task network domains from partially observed plan traces
Abstract Hierarchical Task Network (HTN) planning is an effective yet knowledge intensive
problem-solving technique. It requires humans to encode knowledge in the form of methods …
problem-solving technique. It requires humans to encode knowledge in the form of methods …
On‐line case‐based planning
Some domains, such as real‐time strategy (RTS) games, pose several challenges to
traditional planning and machine learning techniques. In this article, we present a novel on …
traditional planning and machine learning techniques. In this article, we present a novel on …