Learning to Plan with Logical Automata
Author(s)
Araki, Brandon
Vodrahalli, Kiran
Leech, Thomas
Vasile, Cristian-Ioan
Donahue, Mark D.
Rus, Daniela L
Date Issued
June 2019
Journal
Robotics: Science and Systems 2019
Publisher
Robotics: Science and Systems Foundation
Citation
Araki, Brandon et al. "Learning to Plan with Logical Automata." Robotics: Science and Systems 2019, June 2019, Freiburg, Germany, Robotics: Science and Systems Foundation, June 2019
Version
Author's final manuscript
Abstract
This paper introduces the Logic-based Value Iteration Network (LVIN) framework, which combines imitation
learning and logical automata to enable agents to learn complex behaviors from demonstrations. We address two problems with learning from expert knowledge: (1) how to generalize learned policies for a task to larger classes of tasks, and (2) how to account for erroneous demonstrations. Our LVIN model solves finite gridworld environments by instantiating a recurrent, convolutional neural network as a value iteration procedure over a learned Markov Decision Process (MDP) that factors into two MDPs: a small finite state automaton (FSA) corresponding to
logical rules, and a larger MDP corresponding to motions in the environment. The parameters of LVIN (value function, reward map, FSA transitions, large MDP transitions) are approximately learned from expert trajectories. Since the model represents the learned rules as an FSA, the model is interpretable; since the FSA is integrated into planning, the behavior of the agent can be manipulated by modifying the FSA transitions. We demonstrate
these abilities in several domains of interest, including a lunchboxpacking manipulation task and a driving domain.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Lincoln Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.15607/rss.2019.xv.064
