Learning First-Order Symbolic Planning Representations from Plain Graphs

09/12/2019
by   Blai Bonet, et al.
0

One of the main obstacles for developing flexible AI system is the split between data-based learners and model-based solvers. Solvers such as classical planners are very flexible and can deal with a variety of problem instances and goals but require first-order symbolic models. Data-based learners, on the other hand, are robust but do not produce such representations. In this work we address this split by showing how the first-order symbolic representations that are used by planners can be learned from non-symbolic representations alone given by a number of observed system trajectories organized as graphs. The observations can be arbitrary, including raw images. What it is required is that two observations are different iff they proceed from different states. The representation learning problem is formulated as the problem of inferring the simplest planning instances over a common first-order domain that can generate the structures of the observed graphs. A slightly richer version of the problem is also considered where actions are also observed and the graphs are labeled. The problem is expressed and solved via a SAT formulation that is shown to produce first-order representations for domains like Gripper, Blocks, and Hanoi. The work suggests that the target symbolic representations for planning encode the structure of the observed state space, not the observations themselves, as assumed in deep learning approaches.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/25/2022

Learning First-Order Symbolic Planning Representations That Are Grounded

Two main approaches have been developed for learning first-order plannin...
research
05/23/2021

Learning First-Order Representations for Planning from Black-Box States: New Results

Recently Bonet and Geffner have shown that first-order representations f...
research
06/06/2018

Model-free, Model-based, and General Intelligence

During the 60s and 70s, AI researchers explored intuitions about intelli...
research
08/09/2023

Learning Type-Generalized Actions for Symbolic Planning

Symbolic planning is a powerful technique to solve complex tasks that re...
research
04/27/2020

Learning Neural-Symbolic Descriptive Planning Models via Cube-Space Priors: The Voyage Home (to STRIPS)

We achieved a new milestone in the difficult task of enabling agents to ...
research
11/25/2022

Learning Visual Planning Models from Partially Observed Images

There has been increasing attention on planning model learning in classi...
research
06/16/2021

Contrastive Reinforcement Learning of Symbolic Reasoning Domains

Abstract symbolic reasoning, as required in domains such as mathematics ...

Please sign up or login with your details

Forgot password? Click here to reset