Towards Learning Foundation Models for Heuristic Functions to Solve Pathfinding Problems
This addresses efficiency and adaptability issues in AI-driven solutions for pathfinding problems in robotics, computational science, and natural sciences, though it builds incrementally on DeepCubeA.
The paper tackles the problem of requiring domain-specific training for pathfinding problems by introducing a foundation model that learns heuristic functions adaptable to new domains without fine-tuning. The model achieves strong correlation between learned and ground truth heuristic values across various domains, as shown by robust R-squared and Concordance Correlation Coefficient metrics.
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.