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...

Descripción completa

Detalles Bibliográficos
Autores principales: Kuo, Yen-Ling, Katz, Boris, Barbu, Andrei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Robotics and AI
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8326833/
https://www.ncbi.nlm.nih.gov/pubmed/34350213
http://dx.doi.org/10.3389/frobt.2021.689550

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8326833/
https://www.ncbi.nlm.nih.gov/pubmed/34350213
http://dx.doi.org/10.3389/frobt.2021.689550

Ejemplares similares