Searched for: +
(1 - 2 of 2)
document
De Weerdt, E. (author), Van Kampen, E. (author), Chu, Q.P. (author), Mulder, J.A. (author)
Trajectory optimization has been a large field of research for many years. The drawback is that for non-convex, constrained problems practically all available solvers cannot guarantee that the globally optimal trajectory is found. Interval analysis based solvers however can provide this guarantee. Interval analysis has been applied to trajectory...
conference paper 2011
document
De Weerdt, E. (author), Chu, Q.P. (author), Mulder, J.A. (author)
The problem of output optimization within a specified input space of neural networks (NNs) with fixed weights is discussed in this paper. The problem is (highly) nonlinear when nonlinear activation functions are used. This global optimization problem is encountered in the reinforcement learning (RL) community. Interval analysis is applied to...
journal article 2009