Reinforcement learning using the game of soccer
Trial and error learning methods are often ineffective when applied to robots. This is due to certain characteristics found in robotic domains such as large continuous state spaces, noisy sensors and faulty actuators. Learning algorithms work best with small discrete state spaces, discrete determ...
| Main Author: | |
|---|---|
| Language: | English |
| Published: |
2009
|
| Online Access: | http://hdl.handle.net/2429/5465 |