Vai al contenuto principale della pagina

Value and reward based learning in neurorobots / / topic editors, Jeffrey L. Krichmar and Florian Röhrbein



(Visualizza in formato marc)    (Visualizza in BIBFRAME)

Autore: Jeffrey L. Krichmar Visualizza persona
Titolo: Value and reward based learning in neurorobots / / topic editors, Jeffrey L. Krichmar and Florian Röhrbein Visualizza cluster
Pubblicazione: Frontiers Media SA, 2015
[Lausanne, Switzerland] : , : Frontiers Media SA, , 2015
Descrizione fisica: 1 online resource (158 pages) : illustrations; digital, PDF file(s)
Soggetto topico: Reinforcement learning
Soggetto non controllato: reward-based learning
basal ganglia
embodied cognition
value system
neurorobotics
action selection
Neuromodulation
reinforcement learning
Persona (resp. second.): KrichmarJeffrey L.
RöhrbeinFlorian
Nota di bibliografia: Includes bibliographical references.
Sommario/riassunto: Organisms are equipped with value systems that signal the salience of environmental cues to their nervous system, causing a change in the nervous system that results in modification of their behaviour. These systems are necessary for an organism to adapt its behaviour when an important environmental event occurs. A value system constitutes a basic assumption of what is good and bad for an agent. These value systems have been effectively used in robotic systems to shape behaviour. For example, many robots have used models of the dopaminergic system to reinforce behaviour that leads to rewards. Other modulatory systems that shape behaviour are acetylcholine’s effect on attention, norepinephrine’s effect on vigilance, and serotonin’s effect on impulsiveness, mood, and risk. Moreover, hormonal systems such as oxytocin and its effect on trust constitute as a value system. We seek to gather papers on research involving neurobiologically inspired robots whose behaviour is: 1) Shaped by value and reward learning, 2) adapted through interaction with the environment, and 3) shaped by extracting value from the environment.
Titolo autorizzato: Value and reward based learning in neurorobots  Visualizza cluster
ISBN: 9782889194315
Formato: Materiale a stampa
Livello bibliografico Monografia
Lingua di pubblicazione: Inglese
Record Nr.: 9910137529903321
Lo trovi qui: Univ. Federico II
Opac: Controlla la disponibilità qui