Zobrazeno 1 - 10
of 314
pro vyhledávání: '"Lutter Michael"'
Publikováno v:
Main Group Metal Chemistry, Vol 41, Iss 3-4, Pp 109-113 (2018)
The syntheses and structures of tert-butylaminomethyl(mesityl)phosphinic acid ethyl ester 2 and its zinc dichloride complex 3 are reported. In the solid state, both compounds are dimeric via hydrogen bridges. In the complex 3, the phosphinic acid est
Externí odkaz:
https://doaj.org/article/3e0ad5958b2a4fab9016387c1b01fdc6
Model-based reinforcement learning is one approach to increase sample efficiency. However, the accuracy of the dynamics model and the resulting compounding error over modelled trajectories are commonly regarded as key limitations. A natural question
Externí odkaz:
http://arxiv.org/abs/2303.03955
Publikováno v:
Main Group Metal Chemistry, Vol 36, Iss 3-4, Pp 77-82 (2013)
The synthesis of the 2,8-dioxa-5-aza-1-stanna-bicyclo[3.3.01.5]octane [PhN(CH2CH2O)2Sn]n (3) by a combined ligand exchange/redox reaction and independently by the reaction of tin(II)butoxide with N-phenyldiethanolamine is reported. Compound 3 was cha
Externí odkaz:
https://doaj.org/article/54dd4f1230f3424bbe928d4cbd3a1673
Publikováno v:
Main Group Metal Chemistry, Vol 35, Iss 1-2, Pp 41-52 (2012)
The reaction of the silanes X2SiCl2 (X=H, Cl) with the dilithium salts of N-phenyldiethanolamine (1) and N-4-fluorophenyl-di-(2-dimethylpropan-2-ol)amine (2), respectively, gave the novel 5-aza-2,8-dioxasilabicyclo[3.3.01.5]octanes RN(CH2CR′2O)2SiX
Externí odkaz:
https://doaj.org/article/324646ec32da4db2ad515a9e305cee53
Model-based value expansion methods promise to improve the quality of value function targets and, thereby, the effectiveness of value function learning. However, to date, these methods are being outperformed by Dyna-style algorithms with conceptually
Externí odkaz:
http://arxiv.org/abs/2203.14660
Obtaining dynamics models is essential for robotics to achieve accurate model-based controllers and simulators for planning. The dynamics models are typically obtained using model specification of the manufacturer or simple numerical methods such as
Externí odkaz:
http://arxiv.org/abs/2110.12422
Solving the Hamilton-Jacobi-Bellman equation is important in many domains including control, robotics and economics. Especially for continuous control, solving this differential equation and its extension the Hamilton-Jacobi-Isaacs equation, is impor
Externí odkaz:
http://arxiv.org/abs/2110.01954
Autor:
Lutter, Michael, Peters, Jan
Deep learning has been widely used within learning algorithms for robotics. One disadvantage of deep networks is that these networks are black-box representations. Therefore, the learned approximations ignore the existing knowledge of physics or robo
Externí odkaz:
http://arxiv.org/abs/2110.01894
Autor:
Lutter, Michael, Hasenclever, Leonard, Byravan, Arunkumar, Dulac-Arnold, Gabriel, Trochim, Piotr, Heess, Nicolas, Merel, Josh, Tassa, Yuval
Model-Based Reinforcement Learning involves learning a \textit{dynamics model} from data, and then using this model to optimise behaviour, most often with an online \textit{planner}. Much of the recent research along these lines presents a particular
Externí odkaz:
http://arxiv.org/abs/2109.14311