PDSketch: Integrated Domain Programming, Learning, and PlanningDownload PDF

Published: 31 Oct 2022, Last Modified: 11 Oct 2022NeurIPS 2022 AcceptReaders: Everyone
Keywords: Model-Based Learning, Neuro-Symbolic Programming, Heuristic Planning
Abstract: This paper studies a model learning and online planning approach towards building flexible and general robots. Specifically, we investigate how to exploit the locality and sparsity structures in the underlying environmental transition model to improve model generalization, data-efficiency, and runtime-efficiency. We present a new domain definition language, named PDSketch. It allows users to flexibly define high-level structures in the transition models, such as object and feature dependencies, in a way similar to how programmers use TensorFlow or PyTorch to specify kernel sizes and hidden dimensions of a convolutional neural network. The details of the transition model will be filled in by trainable neural networks. Based on the defined structures and learned parameters, PDSketch automatically generates domain-independent planning heuristics without additional training. The derived heuristics accelerate the performance-time planning for novel goals.
Supplementary Material: pdf
TL;DR: We present a planning domain language for exploiting the locality and sparsity structures in the underlying environmental transition model to improve model generalization, data-efficiency, and runtime-efficiency.
15 Replies

Loading