Publication

Novelty of Behaviour as a Basis for the Neuro-evolution of Operant Reward Learning

Andrea Soltoggio
2009
Article de conférence
Résumé

An agent that deviates from a usual or previous course of action can be said to display novel or varying behaviour. Novelty of behaviour can be seen as the result of real or apparent randomness in decision making, which prevents an agent from repeating exactly past choices. In this paper, novelty of behaviour is considered as an evolutionary precursor of the exploring skill in reward learning, and conservative behaviour as the precursor of exploitation. Novelty of behaviour in neural control is hypothesised to be an important factor in the neuro-evolution of operant reward learning. Agents capable of varying behaviour, as opposed to conservative, when exposed to reward stimuli appear to acquire on a faster evolutionary scale the meaning and use of such reward information. The hypothesis is validated by comparing the performance during evolution in two environments that either favour or are neutral to novelty. Following these findings, we suggest that neuro-evolution of operant reward learning is fostered by environments where behavioural novelty is intrinsically beneficial, i.e. where varying or exploring behaviour is associated with low risk.

À propos de ce résultat
Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.
Concepts associés (38)
Consumer behaviour
Consumer behaviour is the study of individuals, groups, or organisations and all the activities associated with the purchase, use and disposal of goods and services. Consumer behaviour consists of how the consumer's emotions, attitudes, and preferences affect buying behaviour. Consumer behaviour emerged in the 1940–1950s as a distinct sub-discipline of marketing, but has become an interdisciplinary social science that blends elements from psychology, sociology, social anthropology, anthropology, ethnography, ethnology, marketing, and economics (especially behavioural economics).
Sciences comportementales
Le terme de sciences comportementales regroupe les disciplines qui explorent les activités et les interactions entre les organismes qui vivent dans la nature. Cela implique analyses systématiques et recherches sur le comportement animal et humain au moyen d'observations contrôlées et naturelles ainsi que des expérimentations scientifiques rigoureuses. Elles visent des conclusions légitimes à travers des formulations rigoureuses. Des exemples d'études comportementales se constituent à travers la psychologie, les sciences cognitives et l'anthropologie.
Système de récompense
Le système de récompense / renforcement aussi appelé système hédonique, est un système fonctionnel fondamental des mammifères, situé dans le cerveau, le long du faisceau médian du télencéphale. Ce système de « récompenses » est indispensable à la survie, car il fournit la motivation nécessaire à la réalisation d'actions ou de comportements adaptés, permettant de préserver l'individu et l'espèce (prise de risque nécessaire à la survie, recherche de nourriture, reproduction, évitement des dangers, etc.).
Afficher plus
Publications associées (47)

Social Opinion Formation and Decision Making Under Communication Trends

Ali H. Sayed, Mert Kayaalp, Virginia Bordignon

This work studies the learning process over social networks under partial and random information sharing. In traditional social learning models, agents exchange full belief information with each other while trying to infer the true state of nature. We stud ...
Piscataway2024

Impact of Mitofusin 2 in the Nucleus Accumbens on motivated behavior and underlying neurobiological mechanisms

Alessandro Chioino

The nucleus accumbens (NAc) is part of the ventral striatum and plays a major role in motivation and goal-directed behaviour. Increasing evidence implicates impairments in accumbal function in anxiety and depression, two conditions that are commonly accomp ...
EPFL2024

Unveiling the complexity of learning and decision-making

Wei-Hsiang Lin

Reinforcement learning (RL) is crucial for learning to adapt to new environments. In RL, the prediction error is an important component that compares the expected and actual rewards. Dopamine plays a critical role in encoding these prediction errors. In my ...
EPFL2024
Afficher plus
MOOCs associés (10)
Neuronal Dynamics 2- Computational Neuroscience: Neuronal Dynamics of Cognition
This course explains the mathematical and computational models that are used in the field of theoretical neuroscience to analyze the collective dynamics of thousands of interacting neurons.
Neuronal Dynamics 2- Computational Neuroscience: Neuronal Dynamics of Cognition
This course explains the mathematical and computational models that are used in the field of theoretical neuroscience to analyze the collective dynamics of thousands of interacting neurons.
Neuronal Dynamics - Computational Neuroscience of Single Neurons
The activity of neurons in the brain and the code used by these neurons is described by mathematical neuron models at different levels of detail.
Afficher plus