Compositional RL Agents That Follow Language Commands in Temporal Logic

We demonstrate how a reinforcement learning agent can use compositional recurrent neural networks to learn to carry out commands specified in linear temporal logic (LTL). Our approach takes as input an LTL formula, structures a deep network according to the parse of the formula, and determines satis...

Full description

Bibliographic Details
Main Authors: Kuo, Yen-Ling (Author), Katz, Boris (Author), Barbu, Andrei (Author)
Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor)
Format: Article
Language:English
Published: Frontiers Media SA, 2021-10-12T13:33:19Z.
Subjects:
Online Access:Get fulltext