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

TL;DR

This paper advances the learning of first-order planning representations from black-box states by employing ASP encodings, improving efficiency, transparency, and robustness to partial or noisy data.

Contribution

It introduces ASP-based encodings using CLINGO for learning first-order domain descriptions, enhancing efficiency and extending capabilities over previous SAT-based methods.

Findings

More efficient domain learning, often optimally solved.

Enhanced transparency and model exploration.

Robustness to partial and noisy state data.

Abstract

Recently Bonet and Geffner have shown that first-order representations for planning domains can be learned from the structure of the state space without any prior knowledge about the action schemas or domain predicates. For this, the learning problem is formulated as the search for a simplest first-order domain description D that along with information about instances I_i (number of objects and initial state) determine state space graphs G(P_i) that match the observed state graphs G_i where P_i = (D, I_i). The search is cast and solved approximately by means of a SAT solver that is called over a large family of propositional theories that differ just in the parameters encoding the possible number of action schemas and domain predicates, their arities, and the number of objects. In this work, we push the limits of these learners by moving to an answer set programming (ASP) encoding using the CLINGO system. The new encodings are more transparent and concise, extending the range of possible models while facilitating their exploration. We show that the domains introduced by Bonet and Geffner can be solved more efficiently in the new approach, often optimally, and furthermore, that the approach can be easily extended to handle partial information about the state graphs as well as noise that prevents some states from being distinguished.