Variable risk policy search for dynamic robot control
A central goal of the robotics community is to develop general optimization algorithms for producing high-performance dynamic behaviors in robot systems. This goal is challenging because many robot control tasks are characterized by significant stochasticity, high-dimensionality, expensive evaluatio...
| Main Author: | |
|---|---|
| Language: | ENG |
| Published: |
ScholarWorks@UMass Amherst
2012
|
| Subjects: | |
| Online Access: | https://scholarworks.umass.edu/dissertations/AAI3545957 |