Batch reinforcement learning on a RoboCup Small Size League keepaway strategy learning problem

Franco Ollino, Miguel A. Solis, Héctor Allende

Resultado de la investigación: Contribución a los tipos de informe/libroContribución a la conferenciarevisión exhaustiva

2 Citas (Scopus)

Resumen

Robotic soccer provides an adversarial scenario where collaborative agents have to execute actions by following a hand-coded or a learned strategy, which in the case of the Small Size League, is given by a centralized decision maker. This work takes advantage of this centralized approach for modelling the keepaway strategy learning problem which is inherently multi-agent, as a single-agent problem, where now each robot forms part of the state of the model. One of the classical reinforcement learning methods is compared with its batch version in terms of amount of time for learning and concluding about updates efficiency based on experiences reusability.

Idioma originalInglés
Título de la publicación alojadaCRoNe 2018 - Proceedings of the 4th Congress on Robotics and Neuroscience
EditoresCristobal J. Nettle, Miguel A. Solis
EditorialCEUR-WS
ISBN (versión digital)9789560928207
EstadoPublicada - 1 ene 2018
Publicado de forma externa
Evento4th Congress on Robotics and Neuroscience, CRoNe 2018 - Valparaiso, Chile
Duración: 15 nov 201817 nov 2018

Serie de la publicación

NombreCEUR Workshop Proceedings
Volumen2312
ISSN (versión impresa)1613-0073

Conferencia

Conferencia4th Congress on Robotics and Neuroscience, CRoNe 2018
País/TerritorioChile
CiudadValparaiso
Período15/11/1817/11/18

Áreas temáticas de ASJC Scopus

  • Informática (todo)

Huella

Profundice en los temas de investigación de 'Batch reinforcement learning on a RoboCup Small Size League keepaway strategy learning problem'. En conjunto forman una huella única.

Citar esto