Keyframe Sampling, Optimization, and Behavior Integration: A New Longest Kick in the RoboCup 3D Simulation League
| dc.contributor.advisor | Stone, Peter | en |
| dc.creator | Depinet, Mike | en |
| dc.date.accessioned | 2014-12-11T15:03:09Z | en |
| dc.date.available | 2014-12-11T15:03:09Z | en |
| dc.date.issued | 2014-05-02 | en |
| dc.description.abstract | Even with improvements in machine learning enabling robots to quickly optimize and perfect their skills, developing a seed skill from which to begin an optimization remains a necessary challenge for large action spaces. This thesis proposes a method for creating and using such a seed by i) observing the effects of the actions of another robot, ii) further optimizing the skill starting from this seed, and iii) em- bedding the optimized skill in a full behavior. Called KSOBI, this method is fully implemented and tested in the complex RoboCup 3D simulation domain. The main result is a kick that, to the best of our knowledge, kicks the ball farther in this simulator than has been previously documented. | en |
| dc.description.department | Computer Science | |
| dc.identifier.uri | http://hdl.handle.net/2152/27772 | en |
| dc.language.iso | eng | en |
| dc.subject | robotics | en |
| dc.subject | RoboCup 3D simulation | en |
| dc.subject | optimization | en |
| dc.subject | seed skill | en |
| dc.subject | keyframe sampling | en |
| dc.title | Keyframe Sampling, Optimization, and Behavior Integration: A New Longest Kick in the RoboCup 3D Simulation League | en |
| dc.type | Thesis | en |