Corpus ID: 24294341

Towards learning domain-independent planning heuristics

  title={Towards learning domain-independent planning heuristics},
  author={Pawel Gomoluch and Dalal Alrajeh and Alessandra Russo and Antonio Bucchiarone},
Automated planning remains one of the most general paradigms in Artificial Intelligence, providing means of solving problems coming from a wide variety of domains. One of the key factors restricting the applicability of planning is its computational complexity resulting from exponentially large search spaces. Heuristic approaches are necessary to solve all but the simplest problems. In this work, we explore the possibility of obtaining domain-independent heuristic functions using machine… Expand
Learning Domain-Independent Planning Heuristics with Hypergraph Networks
This work presents the first approach capable of learning domain-independent planning heuristics entirely from scratch, and shows that the heuristically learned are able to generalise across different problems and domains, including to domains that were not seen during training. Expand
Meta Reinforcement Learning for Heuristic Planing
This work makes a connection between meta-reinforcement learning and heuristic planning, showing that heuristic functions meta-learned from planning problems, in a given domain, can outperform both popular domain-independent heuristics, and heuristic learned by supervised learning. Expand
Learning Search-Space Specific Heuristics Using Neural Network
We propose and evaluate a system which learns a neuralnetwork heuristic function for forward search-based, satisficing classical planning. Our system learns distance-to-goal estimators from scratch,Expand
Learning Delete-Relaxation Heuristics over Hypergraphs
We present the first approach capable of learning domainindependent planning heuristics entirely from scratch. The heuristics we learn map the hypergraph representation of the delete-relaxation ofExpand
Finding Macro-Actions with Disentangled Effects for Efficient Planning with the Goal-Count Heuristic
This work constructs macro-actions with disentangled effects that dramatically improve planning efficiency for 15-puzzle and Rubik's cube, reliably solving each domain without prior knowledge, and solving Rubik’s cube with orders of magnitude less data than competing approaches. Expand
Asymptotically Optimal Pruning for Nonholonomic Nearest-Neighbor Search
This work proposes efficient pruning techniques for the $k$-d tree algorithm that drastically reduce the number of distance evaluations performed during a query, and provides experimental results with the Reeds-Shepp vehicle model. Expand
Efficient Black-Box Planning Using Macro-Actions with Focused Effects
The method discovers macros that dramatically improve black-box planning efficiency across a wide range of planning domains, including Rubik's cube, where it generates fewer states than the state-of-the-art LAMA planner with access to the full SAS$^+$ representation. Expand


Learning Control Knowledge for Forward Search Planning
This work introduces a novel feature space for representing control knowledge in terms of information computed via relaxed plan extraction, which has been a major source of success for non-learning planners and gives a new way of leveraging relaxed planning techniques in the context of learning. Expand
A Robust and Fast Action Selection Mechanism for Planning
A variation of Korf's Learning Real Time A* algorithm together with a suitable heuristic function is developed by looking at planning as real time search and the resulting algorithm interleaves lookahead with execution and never builds a plan. Expand
The FF Planning System: Fast Plan Generation Through Heuristic Search
A novel search strategy is introduced that combines hill-climbing with systematic search, and it is shown how other powerful heuristic information can be extracted and used to prune the search space. Expand
Learning and Executing Generalized Robot Plans
Some major new additions to the STRIPS robot problem-solving system are described, including a process for generalizing a plan produced by STriPS so that problem-specific constants appearing in the plan are replaced by problem-independent parameters. Expand
The 1998 AI Planning Systems Competition
The 1998 Planning Competition at the AI Planning Systems Conference was the first of its kind to create planning domains that a wide variety of planning researchers could agree on to make comparison among planners more meaningful, and set up a framework for long-term creation of a repository of problems in a standard notation. Expand
The Computational Complexity of Propositional STRIPS Planning
  • T. Bylander
  • Mathematics, Computer Science
  • Artif. Intell.
  • 1994
For these types of restrictions, it is shown when planning is tractable (polynomial) and intractable (NP-hard) and PSPACE-complete to determine if a given planning instance has any solutions. Expand
STRIPS: A New Approach to the Application of Theorem Proving to Problem Solving
We describe a new problem solver called STRIPS that attempts to find a sequence of operators in a space of world models to transform a given initial world model into a model in which a given goalExpand
Artificial Intelligence
The history, the major landmarks, and some of the controversies in each of these twelve topics are discussed, as well as some predictions about the course of future research. Expand
Scikit-learn: Machine Learning in Python
Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems. This package focuses on bringingExpand
Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit
The model of cortical processing is presented as an electronic circuit that emulates this hybrid operation, and so is able to perform computations that are similar to stimulus selection, gain modulation and spatiotemporal pattern generation in the neocortex. Expand