1.

Record Nr.

UNINA9910137529903321

Autore

Jeffrey L. Krichmar

Titolo

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

Pubbl/distr/stampa

Frontiers Media SA, 2015

[Lausanne, Switzerland] : , : Frontiers Media SA, , 2015

ISBN

9782889194315

Descrizione fisica

1 online resource (158 pages) : illustrations; digital, PDF file(s)

Collana

Frontiers Research Topics

Soggetti

Reinforcement learning

Lingua di pubblicazione

Inglese

Formato

Materiale a stampa

Livello bibliografico

Monografia

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.