Unsupervised Grounding of Plannable First-Order Logic Representation from Images
Author:
Preprint
Abstract
Recently, there is an increasing interest in obtaining the relational structures of the environment in the Reinforcement Learning community. However, the resulting "relations" are not the discrete, logical predicates compatible to the symbolic reasoning such as classical planning or goal recognition. Meanwhile, Latplan (Asai and Fukunaga 2018) bridged the gap between deep-learning perceptual systems and symbolic classical planners. One key component of the system is a Neural Network called State AutoEncoder (SAE), which encodes an image-based input into a propositional representation compatible to classical planning. To get the best of both worlds, we propose First-Order State AutoEncoder, an unsupervised architecture for grounding the first-order logic predicates and facts. Each predicate models a relationship between objects by taking the interpretable arguments and returning a propositional value. In the experiment using 8-Puzzle and a photo-realistic Blocksworld environment, we show that (1) the resulting predicates capture the interpretable relations (e.g. spatial), (2) they help obtaining the compact, abstract model of the environment, and finally, (3) the resulting model is compatible to symbolic classical planning.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Lifted Relational Neural Networks: Efficient Learning of Latent Relational StructuresJournal of Artificial Intelligence Research, 2018
- Hybrid computing using a neural network with dynamic external memoryNature, 2016
- Acquiring planning domain models using LOCMThe Knowledge Engineering Review, 2013
- A survey of named entity recognition and classification2007
- Learning action models from plan examples using weighted MAX-SATArtificial Intelligence, 2007
- The FF Planning System: Fast Plan Generation Through Heuristic SearchJournal of Artificial Intelligence Research, 2001
- Learning distributed representations of concepts using linear relational embeddingIEEE Transactions on Knowledge and Data Engineering, 2001
- The symbol grounding problemPhysica D: Nonlinear Phenomena, 1990