Compositional RL Agents That Follow Language Commands in Temporal Logic
We demonstrate how a reinforcement learning agent can use compositional recurrent neural net- works 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 sat...
Main Authors: | Kuo, Yen-Ling, Barbu, Andrei, Katz, Boris |
---|---|
Format: | Article |
Published: |
Center for Brains, Minds and Machines (CBMM), Frontiers in Robotics and AI
2022
|
Online Access: | https://hdl.handle.net/1721.1/141357 |
Similar Items
-
Compositional RL Agents That Follow Language Commands in Temporal Logic
by: Kuo, Yen-Ling, et al.
Published: (2021) -
Deep compositional robotic planners that follow natural language commands
by: Kuo, Yen-Ling, et al.
Published: (2022) -
Compositional Networks Enable Systematic Generalization for Grounded Language Understanding
by: Kuo, Yen-Ling, et al.
Published: (2022) -
Learning a natural-language to LTL executable semantic parser for grounded robotics
by: Wang, Christopher, et al.
Published: (2022) -
Encoding formulas as deep networks: Reinforcement learning for zero-shot execution of LTL formulas
by: Kuo, Yen-Ling, et al.
Published: (2022)