A bioinspired hierarchical reinforcement learning architecture for modeling learning of multiple skills with continuous state and actions

Autor: Caligiore D., Mirolli M., Parisi D., Baldassarre Gi.

Publikováno v: Tenth International Conference on Epigenetic Robotics (EpiRob2010), Sweden, 5-7/11/2010
info:cnr-pdr/source/autori:Caligiore D., Mirolli M., Parisi D., Baldassarre Gi./congresso_nome:Tenth International Conference on Epigenetic Robotics (EpiRob2010)/congresso_luogo:Sweden/congresso_data:5-7%2F11%2F2010/anno:2010/pagina_da:/pagina_a:/intervallo_pagine

Organisms, and especially primates, are able to learn several skills while avoiding catastrophic interference and enhancing generalisation. This paper proposes a novel hierarchical reinforcement learning (RL) architecture with a number of features th

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=cnr_________::668fe2495962a0918cfdf8ade8a88c75
https://publications.cnr.it/doc/140241