Decision-Focused Learning to Predict Action Costs for Planning

TL;DR

This paper introduces decision-focused learning for predicting action costs in automated planning, addressing unique challenges in gradient computation and scalability, and demonstrating improved planning outcomes over traditional prediction methods.

Contribution

It pioneers the application of decision-focused learning to automated planning, proposing novel gradient computation methods and caching techniques to enhance scalability and effectiveness.

Findings

Decision-focused learning outperforms traditional prediction in planning quality.

Proposed gradient methods effectively handle negative action costs.

Caching mechanisms improve training efficiency.

Abstract

In many automated planning applications, action costs can be hard to specify. An example is the time needed to travel through a certain road segment, which depends on many factors, such as the current weather conditions. A natural way to address this issue is to learn to predict these parameters based on input features (e.g., weather forecasts) and use the predicted action costs in automated planning afterward. Decision-Focused Learning (DFL) has been successful in learning to predict the parameters of combinatorial optimization problems in a way that optimizes solution quality rather than prediction quality. This approach yields better results than treating prediction and optimization as separate tasks. In this paper, we investigate for the first time the challenges of implementing DFL for automated planning in order to learn to predict the action costs. There are two main challenges to overcome: (1) planning systems are called during gradient descent learning, to solve planning problems with negative action costs, which are not supported in planning. We propose novel methods for gradient computation to avoid this issue. (2) DFL requires repeated planner calls during training, which can limit the scalability of the method. We experiment with different methods approximating the optimal plan as well as an easy-to-implement caching mechanism to speed up the learning process. As the first work that addresses DFL for automated planning, we demonstrate that the proposed gradient computation consistently yields significantly better plans than predictions aimed at minimizing prediction error; and that caching can temper the computation requirements.