Cargando…
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...
Autores principales: | Kuo, Yen-Ling, Katz, Boris, Barbu, Andrei |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
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 |
Ejemplares similares
-
Network Layer Analysis for a RL-Based Robotic Reaching Task
por: Feldotto, Benedikt, et al.
Publicado: (2022) -
Coordinating Shared Tasks in Human-Robot Collaboration by Commands
por: Angleraud , Alexandre, et al.
Publicado: (2021) -
Robust Understanding of Robot-Directed Speech Commands Using Sequence to Sequence With Noise Injection
por: Tada, Yuuki, et al.
Publicado: (2020) -
A data-driven approach for motion planning of industrial robots controlled by high-level motion commands
por: Hou, Shuxiao, et al.
Publicado: (2023) -
Human-Guided Learning for Probabilistic Logic Models
por: Odom, Phillip, et al.
Publicado: (2018)