Title :
Task-level learning: experiments and extensions
Author :
Branicky, Michael S.
Author_Institution :
AI Lab., MIT, Cambridge, MA, USA
Abstract :
Results obtained from experiments with task-level learning are described. The main idea of task-level learning is that a given task can be viewed as an input-output system driven by a vector of input variables or commands and responding with a vector of output variables or performance indicators. This formulation allows the application of powerful numerical methods to problems at a high-level of performance measurement: the task level. Task-level learning is studied as a paradigm than may help to program machines to learn from experience in order to: (1) perform a task better over time, (2) optimize task performance, and (3) generalize knowledge over tasks. Some extensions to the paradigm are explored. A refined model learning scheme is presented. Simulation experiments are performed to test the effects of different inverse models, different learning schemes, and different learning intervals. A framework for dealing with tasks that inherently try to minimize or maximize performance is presented
Keywords :
learning systems; optimisation; input-output system; inverse models; learning intervals; model learning scheme; numerical methods; performance measurement; task performance optimisation; task-level learning; Artificial intelligence; Input variables; Intelligent robots; Inverse problems; Iterative algorithms; Laboratories; Machine learning; Measurement; Performance evaluation; Testing;
Conference_Titel :
Robotics and Automation, 1991. Proceedings., 1991 IEEE International Conference on
Conference_Location :
Sacramento, CA
Print_ISBN :
0-8186-2163-X
DOI :
10.1109/ROBOT.1991.131585