SIAMCO
2008
14 years 8 months ago
2008
We introduce a new class of control problems in which the gain depends on the solution of a stochastic differential equation reflected at the boundary of a bounded domain, along d...
NIPS
2007
14 years 10 months ago
2007
We combine three threads of research on approximate dynamic programming: sparse random sampling of states, value function and policy approximation using local models, and using lo...