Cargando…
Improving Robot Motor Learning with Negatively Valenced Reinforcement Signals
Both nociception and punishment signals have been used in robotics. However, the potential for using these negatively valenced types of reinforcement learning signals for robot learning has not been exploited in detail yet. Nociceptive signals are primarily used as triggers of preprogrammed action s...
Autores principales: | Navarro-Guerrero, Nicolás, Lowe, Robert J., Wermter, Stefan |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2017
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5376586/ https://www.ncbi.nlm.nih.gov/pubmed/28420976 http://dx.doi.org/10.3389/fnbot.2017.00010 |
Ejemplares similares
-
Learning Then, Learning Now, and Every Second in Between: Lifelong Learning With a Simulated Humanoid Robot
por: Logacjov, Aleksej, et al.
Publicado: (2021) -
Learning indoor robot navigation using visual and sensorimotor map information
por: Yan, Wenjie, et al.
Publicado: (2013) -
Map-based experience replay: a memory-efficient solution to catastrophic forgetting in reinforcement learning
por: Hafez, Muhammad Burhan, et al.
Publicado: (2023) -
Valence biases in reinforcement learning shift across adolescence and modulate subsequent memory
por: Rosenbaum, Gail M, et al.
Publicado: (2022) -
From Semantics to Execution: Integrating Action Planning With Reinforcement Learning for Robotic Causal Problem-Solving
por: Eppe, Manfred, et al.
Publicado: (2019)