Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Eduardo W. Basso"'
Autor:
Mauricio Galassi, Eduardo André Perondi, Hugo Francisco Lisboa Santos, Ney Robinson Salvi Dos Reis, Anselmo Silva, Bruno B. Castro, Igor Mendes Ursine Krettli, Andre Manoel Goja Ferreira, Hardy Leonardo da Cunha Pereira Pinto, Dante Augusto Couto Barone, Eduardo W. Basso, André Viegas Wentz, Lincoln Homero Thomé Ferreira
Publikováno v:
Day 1 Mon, September 30, 2019.
Methane Hydrates and Paraffin Plugs in flexible lines are concerns in offshore production. They may stop wells for months, causing high financial losses. Sometimes, operators use depressurization techniques for hydrate removal. Other strategy is usin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::87f48023905a59560fa53ff7a1db2f83
https://doi.org/10.2118/196015-ms
https://doi.org/10.2118/196015-ms
Autor:
Filipo Studzinski Perotto, Bruno da Silva, Ana L. C. Bazzan, Paulo Martins Engel, Eduardo W. Basso
Publikováno v:
AAMAS
5th International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS 2006), Hakodate, Japan, May 8-12, 2006
5th International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS 2006), Hakodate, Japan, May 8-12, 2006, 2006, New York, NY, USA, United States. pp.810--812, ⟨10.1145/1160633.1160779⟩
5th International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS 2006), Hakodate, Japan, May 8-12, 2006
5th International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS 2006), Hakodate, Japan, May 8-12, 2006, 2006, New York, NY, USA, United States. pp.810--812, ⟨10.1145/1160633.1160779⟩
International audience; In this paper we propose a method for solving reinforcement learning problems in non-stationary environments. The basic idea is to create and simultaneously update multiple partial models of the environment dynamics. The learn
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7680ce5db1c415df8e20ea26c77ffae4
https://doi.org/10.1145/1160633.1160779
https://doi.org/10.1145/1160633.1160779
Publikováno v:
ICML
In this paper we introduce RL-CD, a method for solving reinforcement learning problems in non-stationary environments. The method is based on a mechanism for creating, updating and selecting one among several partial models of the environment. The pa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5682e84fb4135ab66557cc8cadd7b376
https://doi.org/10.1145/1143844.1143872
https://doi.org/10.1145/1143844.1143872