Cargando…
Safe Model-Based Reinforcement Learning for Systems With Parametric Uncertainties
Reinforcement learning has been established over the past decade as an effective tool to find optimal control policies for dynamical systems, with recent focus on approaches that guarantee safety during the learning and/or execution phases. In general, safety guarantees are critical in reinforcement...
Autores principales: | Mahmud, S. M. Nahid, Nivison, Scott A., Bell, Zachary I., Kamalapurkar, Rushikesh |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8717089/ https://www.ncbi.nlm.nih.gov/pubmed/34977161 http://dx.doi.org/10.3389/frobt.2021.733104 |
Ejemplares similares
-
Editorial: Safety in Collaborative Robotics and Autonomous Systems
por: Dani, Ashwin, et al.
Publicado: (2022) -
Modeling Task Uncertainty for Safe Meta-Imitation Learning
por: Matsushima, Tatsuya, et al.
Publicado: (2020) -
Comparing Deep Reinforcement Learning Algorithms’ Ability to Safely Navigate Challenging Waters
por: Larsen, Thomas Nakken, et al.
Publicado: (2021) -
Koopman Operator–Based Knowledge-Guided Reinforcement Learning for Safe Human–Robot Interaction
por: Sinha, Anirban, et al.
Publicado: (2022) -
Modeling Uncertainty for the Double Standard Model Using a Fuzzy Inference System
por: Torres, Noelia, et al.
Publicado: (2018)