Learning First-Order Symbolic Representations for Planning from the Structure of the State Space

By Blai Bonet, Hector Geffner. 2019

68 citations recorded by the source corpus.

One of the main obstacles for developing flexible AI systems 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 inputs that encode the structure of the state space. The representation learning problem is formulated as the problem of inferring planning instances over a common but unknown first-order domain that account for the structure of the observed state space. This means to infer a complete first-order representation (i.e. general action schemas, relational symbols, and objects) that explains the observed state space structures. The inference problem is cast as a two-level combinatorial search where the outer level searches for values of a small set of hyperparameters and the inner level, solved via SAT, searches for a first-order symbolic model. The framework is shown to produce general and correct first-order representations for standard problems like Gripper, Blocksworld, and Hanoi from input graphs that encode the flat state-space structure of a single instance.

Subfields: Artificial Intelligence, Reinforcement Learning, Knowledge Graphs & Representation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Reinforcement Learning

In Knowledge Graphs & Representation

Citations in the corpus

Toward Causal Representation Learning (2021, background): “Hence, the emerging ﬁeld of causal representation learning strives to learn these variables from data, much like machine learning went beyond symbolic AI in not requiring that the symbols that algorithms manipulate be given a priori (see [34]).”
Causality for Machine Learning (2019, background): “The emerging field of causal representation learning hence strives to learn these variables from data, much like machine learning went beyond symbolic AI in not requiring that the symbols that algorithms manipulate be given a priori (cf. Bonet and Geffner (2019)).”
Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning (2023, unknown): “In classical planning, the community has explored numerous learning-based methods [59, 61, 9, 25, 4] and interactive editor-based methods [49] for acquiring symbolic domain models.”
Inventing Relational State and Action Abstractions for Effective and Efficient Bilevel Planning (2022, methodology): “For this, we perform an intersection over all abstract states in each equivalence class [17, 20, 29]: , where δ − 1 τ ( s ) substitutes all occurrences of the objects in s with the parameters in P AR following an inversion of δ τ , and discards any atoms involving objects that are not in the image…”