Content deleted Content added
No edit summary |
m Reverted edits by 128.214.48.206 to last version by Imz (GLOO) |
||
Line 8:
Another method of choice is reinforcement learning, embodied in systems such as [http://www.cs.berkeley.edu/~bhaskara/alisp/ Alisp]. In such systems, rather than backtracking, the system keeps track of some measure of success and learns which choices often lead to success, and in which situations (both internal program state and environmental input may affect the choice). These systems are suitable for applications to [[robotics]] and other domains in which backtracking would involve attempting to undo actions performed in a dynamic environment, which may be difficult or impossible.
==See also==
| |||