Get the latest Science News and Discoveries
Discrete-time rewards efficiently guide the extraction of continuous-time optimal control policy from system data - EurekAlert
In a paper published in National Science Open, an international team of scientists from China, Singapore, and United States of America design a new concept of discrete-time reward under which evidence of extraction of continuous-time optimal control policy from system data is presented. This method has its computational efficiency since it improved computational efficiency by dropping the integrator operator that appears in classical results with integral rewards. The results reveal that it is a data-driven approach without an intermediate stage of identifying dynamical models.
None
Or read this on Eureka Alert