Towards Learning Foundation Models for Heuristic Functions to Solve Pathfinding Problems

TL;DR

This paper presents a foundation model using deep reinforcement learning to generate adaptable heuristic functions for pathfinding, enabling efficient solving of diverse and unseen domains without additional training.

Contribution

The study introduces a novel foundation model that leverages deep reinforcement learning to produce domain-adaptive heuristic functions for pathfinding problems.

Findings

Strong correlation between learned and true heuristics across domains

Model generalizes well to unseen pathfinding problems

Improved adaptability over traditional domain-specific methods

Abstract

Pathfinding problems are found throughout robotics, computational science, and natural sciences. Traditional methods to solve these require training deep neural networks (DNNs) for each new problem domain, consuming substantial time and resources. This study introduces a novel foundation model, leveraging deep reinforcement learning to train heuristic functions that seamlessly adapt to new domains without further fine-tuning. Building upon DeepCubeA, we enhance the model by providing the heuristic function with the domain's state transition information, improving its adaptability. Utilizing a puzzle generator for the 15-puzzle action space variation domains, we demonstrate our model's ability to generalize and solve unseen domains. We achieve a strong correlation between learned and ground truth heuristic values across various domains, as evidenced by robust R-squared and Concordance Correlation Coefficient metrics. These results underscore the potential of foundation models to establish new standards in efficiency and adaptability for AI-driven solutions in complex pathfinding problems.