Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Ângelo Gregório Lovatto"'
Autor:
Ângelo Gregório Lovatto
Publikováno v:
Biblioteca Digital de Teses e Dissertações da USP
Universidade de São Paulo (USP)
instacron:USP
Universidade de São Paulo (USP)
instacron:USP
Stochastic Value Gradient (SVG) methods underlie many recent achievements of model-based Reinforcement Learning (RL) agents in continuous state-action spaces. Such methods use data collected by exploration in the environment to produce a model of its
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::16751d06e66c6b7a3fdd1c73aef0eeb3
https://doi.org/10.11606/d.45.2022.tde-28062022-123656
https://doi.org/10.11606/d.45.2022.tde-28062022-123656
Publikováno v:
Intelligent Systems ISBN: 9783031216886
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b87cc6d7b6b1c579e6d0a65f1e4c61e7
https://doi.org/10.1007/978-3-031-21689-3_3
https://doi.org/10.1007/978-3-031-21689-3_3
Publikováno v:
Intelligent Systems ISBN: 9783030917012
Stochastic Value Gradient (SVG) methods underlie many recent achievements of model-based Reinforcement Learning agents in continuous state-action spaces. Despite their practical significance, many algorithm design choices still lack rigorous theoreti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::98e09e25b477df85b9aa7a93bfca5776
https://doi.org/10.1007/978-3-030-91702-9_3
https://doi.org/10.1007/978-3-030-91702-9_3