Loading...
Please wait, while we are loading the content...
Tuning Optimizers for Time-Constrained Problems using Reinforcement Learning
| Content Provider | Semantic Scholar |
|---|---|
| Author | Ruvolo, Paul |
| Copyright Year | 2008 |
| Abstract | Many popular optimization algorithms, like the Levenberg-Marquardt algorithm (LMA), use heuristic-based “controllers” that modulate the behavior of the optimizer during the optimization process. For example, in the LMA a damping parameter λ is dynamically modified based on a set of rules that were developed using various heuristic arguments. Here we show that a modern reinforcement learning technique utilizing a very simple state space can dramatically improve the performance of general purpose optimizers, like the LMA, on problems where the number of function evaluations allowed is constrained by a budget. Results are given on both classical non-linear optimization problems as well as a difficult computer vision task. Interestingly the controllers learned for a particular optimization domain work well on other optimization domains. Thus, the controller appeared to have extracted optimization rules that were not just domain specific but generalized across a range of optimization domains. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://opt2008.kyb.tuebingen.mpg.de/papers/ruvolo.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
