A unified framework for planning with learned neural network transition models

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

Automated planning with neural network transition models is a two stage approach to solving planning problems with unknown transition models. The first stage of the approach learns the unknown transition model from data as a neural network model, and the second stage of the approach compiles the learned model to either a Mixed-Integer Linear Programming (MILP) model or a Recurrent Neural Network (RNN) model, and optimize it using an off-the-shelf solver. The previous studies have shown that both models have their advantages and disadvantages. Namely, the MILP model can be solved optimally using a branch-and-bound algorithm but has been experimentally shown not to scale well for neural networks with multiple hidden layers. In contrast, the RNN model can be solved effectively using a gradient descent algorithm but can only work under very restrictive assumptions. In this paper, we focus on improving the effectiveness of solving the second stage of the approach by introducing (i) a novel Lagrangian RNN architecture that can model the previously ignored components of the planning problem as Lagrangian functions, and (ii) a novel framework that unifies the MILP and the Lagrangian RNN models such that the weakness of one model is complemented by the strength of the other. Experimentally, we show that our unifying framework significantly outperforms the standalone MILP model by solving 80% more problem instances, and showcase the ability of our unifying framework to find high quality solutions to challenging automated planning problems with unknown transition models.
Original languageEnglish
Title of host publicationProceedings of the AAAI Conference on Artificial Intelligence, AAAI-21
EditorsKevin Leyton-Brown, Mausam
Place of PublicationPalo Alto CA USA
PublisherAssociation for the Advancement of Artificial Intelligence (AAAI)
Pages5016-5024
Number of pages9
Volume35
Edition6
ISBN (Electronic)9781577358664
Publication statusPublished - 2021
EventAAAI Conference on Artificial Intelligence 2021 - Virtual, United States of America
Duration: 2 Feb 20219 Feb 2021
Conference number: 35
https://aaai.org/Conferences/AAAI-21/ (Website)

Conference

ConferenceAAAI Conference on Artificial Intelligence 2021
Abbreviated titleAAAI
CountryUnited States of America
Period2/02/219/02/21
Internet address

Keywords

  • Neuro-Symbolic AI (NSAI)
  • Planning/Scheduling and Learning
  • Mixed Discrete/Continuous Optimization
  • (Deep) Neural Network Algorithms

Cite this