Loading...

Spike-Based Reinforcement Learning in Continuous State and Action Space: When Policy Gradient Methods Fail

Changes of synaptic connections between neurons are thought to be the physiological basis of learning. These changes can be gated by neuromodulators that encode the presence of reward. We study a family of reward-modulated synaptic learning rules for spiking neurons on a learning task in continuous...

Fuld beskrivelse

Na minha lista:
Bibliografiske detaljer
Main Authors: Vasilaki, Eleni, Frémaux, Nicolas, Urbanczik, Robert, Senn, Walter, Gerstner, Wulfram
Format: Artigo
Sprog:Inglês
Udgivet: Public Library of Science 2009
Fag:
Online adgang:https://ncbi.nlm.nih.gov/pmc/articles/PMC2778872/
https://ncbi.nlm.nih.gov/pubmed/19997492
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1371/journal.pcbi.1000586
Tags: Tilføj Tag
Ingen Tags, Vær først til at tagge denne postø!