Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Moldovan, Teodor"'
Model-based Reinforcement Learning with Parametrized Physical Models and Optimism-Driven Exploration
In this paper, we present a robotic model-based reinforcement learning method that combines ideas from model identification and model predictive control. We use a feature-based representation of the dynamics that allows the dynamics model to be fitte
Externí odkaz:
http://arxiv.org/abs/1509.06824
Autor:
Moldovan, Teodor Mihai, Abbeel, Pieter
In environments with uncertain dynamics exploration is necessary to learn how to perform well. Existing reinforcement learning algorithms provide strong exploration guarantees, but they tend to rely on an ergodicity assumption. The essence of ergodic
Externí odkaz:
http://arxiv.org/abs/1205.4810
Publikováno v:
Acta Marisiensis. Seria Medica. 2024 Supplement, Vol. 70, p98-99. 2p.
Autor:
Moldovan, Teodor Mihai
Publikováno v:
Moldovan, Teodor Mihai. (2014). Safety, Risk Awareness and Exploration in Reinforcement Learning. UC Berkeley: Computer Science. Retrieved from: http://www.escholarship.org/uc/item/8mx921bb
Replicating the human ability to solve complex planning problems based on minimal prior knowledge has been extensively studied in the field of reinforcement learning. Algorithms for discrete or approximate models are supported by theoretical guarante
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______325::3eb7737a83c77580dd0f9bacb9566532
http://n2t.net/ark:/13030/m5dc2ppw
http://n2t.net/ark:/13030/m5dc2ppw
Publikováno v:
2016 IEEE International Conference on Robotics & Automation (ICRA); 2016, p504-511, 8p
Autor:
Hunter, Timothy, Moldovan, Teodor, Zaharia, Matei, Merzgui, Samy, Ma, Justin, Franklin, Michael J., Abbeel, Pieter, Bayen, Alexandre M.
Publikováno v:
Proceedings of the 2nd ACM Symposium: Cloud Computing; Oct2011, p1-8, 8p