dc.contributor.author |
Field, Timothy P |
|
dc.date.accessioned |
2011-03-28T20:37:00Z |
|
dc.date.accessioned |
2022-10-25T07:31:02Z |
|
dc.date.available |
2011-03-28T20:37:00Z |
|
dc.date.available |
2022-10-25T07:31:02Z |
|
dc.date.copyright |
2005 |
|
dc.date.issued |
2005 |
|
dc.identifier.uri |
https://ir.wgtn.ac.nz/handle/123456789/23563 |
|
dc.description.abstract |
Until recently it was widely considered that value function-based reinforcement learning methods were the only feasible way of solving general stochastic optimal control problems. Unfortunately, these approaches are inapplicable to real-world problems with continuous, high-dimensional and partially-observable properties such as motor control tasks.
While policy-gradient reinforcement learning methods suggest a suitable approach to such tasks, they suffer from typical parametric learning issues such as model selection and catastrophic forgetting. This thesis investigates the application of policy-gradient learning to a range of simulated motor learning tasks and introduces the use of local factored policies to enable incremental learning in tasks of unknown complexity. |
en_NZ |
dc.format |
pdf |
en_NZ |
dc.language |
en_NZ |
|
dc.language.iso |
en_NZ |
|
dc.publisher |
Te Herenga Waka—Victoria University of Wellington |
en_NZ |
dc.title |
Policy-gradient learning for motor control |
en_NZ |
dc.type |
Text |
en_NZ |
vuwschema.type.vuw |
Awarded Research Masters Thesis |
en_NZ |
thesis.degree.discipline |
Computer Science |
en_NZ |
thesis.degree.grantor |
Te Herenga Waka—Victoria University of Wellington |
en_NZ |
thesis.degree.level |
Masters |
en_NZ |