Adversarial Actor-Critic Method for Task and Motion Planning Problems Using Planning Experience

Authors

  • Beomjoon Kim Massachusetts Institute of Technology
  • Leslie Pack Kaelbling Massachusetts Institute of Technology
  • Tomás Lozano-Pérez Massachusetts Institute of Technology

DOI:

https://doi.org/10.1609/aaai.v33i01.33018017

Abstract

We propose an actor-critic algorithm that uses past planning experience to improve the efficiency of solving robot task-and-motion planning (TAMP) problems. TAMP planners search for goal-achieving sequences of high-level operator instances specified by both discrete and continuous parameters. Our algorithm learns a policy for selecting the continuous parameters during search, using a small training set generated from the search trees of previously solved instances. We also introduce a novel fixed-length vector representation for world states with varying numbers of objects with different shapes, based on a set of key robot configurations. We demonstrate experimentally that our method learns more efficiently from less data than standard reinforcementlearning approaches and that using a learned policy to guide a planner results in the improvement of planning efficiency.

Downloads

Published

2019-07-17

How to Cite

Kim, B., Kaelbling, L. P., & Lozano-Pérez, T. (2019). Adversarial Actor-Critic Method for Task and Motion Planning Problems Using Planning Experience. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 8017-8024. https://doi.org/10.1609/aaai.v33i01.33018017

Issue

Section

AAAI Technical Track: Robotics