| 摘要 |
A machine and method capable of developing intelligent behavior from interaction with its environment directly using the machine's sensors and effectors. The method described is independent of the type of sensors and actuators, or the tasks to be executed, and, therefore, provides a general purpose learner that learns while performing. It senses the world, recalls what is learned, judges what to do and acts according to what it has learned. The machine enables the machine to learn directly from sensory input streams while interacting with the environment, including human teachers. The presented approach enables the system to self-organize its internal representation, and uses a systematic way to automatically build multi-level representation using the Markov random process model. Reward and punishment are combined with sensor-based teaching to develop intelligent behavior.
|
