Lataa...

Estimating scale-invariant future in continuous time

Natural learners must compute an estimate of future outcomes that follow from a stimulus in continuous time. Critically, the learner cannot in general know a priori the relevant time scale over which meaningful relationships will be observed. Widely used reinforcement learning algorithms discretize...

Täydet tiedot

Tallennettuna:
Bibliografiset tiedot
Julkaisussa:Neural Comput
Päätekijät: Tiganj, Zoran, Gershman, Samuel J., Sederberg, Per B., Howard, Marc W.
Aineistotyyppi: Artigo
Kieli:Inglês
Julkaistu: 2019
Aiheet:
Linkit:https://ncbi.nlm.nih.gov/pmc/articles/PMC6959535/
https://ncbi.nlm.nih.gov/pubmed/30764739
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1162/neco_a_01171
Tagit: Lisää tagi
Ei tageja, Lisää ensimmäinen tagi!