Abstract: This paper proposes an optimal gait generation framework based on a property of Hamiltonian systems. A key technique is a unified method of learning control and parameter tuning. The proposed method allows one to simultaneously obtain an optimal feedforward input and an optimal tuning parameter for a plant system, which (at least locally) minimize a cost function. It is a repetitive c...

Typical MT training involves several stages, including word alignment, rule extraction, translation model estimation, and parameter tuning. In this paper, different from the traditional pipeline, we investigate the possibility of end-to-end MT training, and propose a framework which combines rule induction and parameter tuning in one single module. Preliminary experiments show that our learned ...

Optimizing parameter settings is an important task in algorithm design. Several automated parameter tuning procedures/configurators have been proposed in the literature, most of which work effectively when given a good initial range for the parameter values. In the Design of Experiments (DOE), a good initial range is known to lead to an optimum parameter setting. In this paper, we present a fra...