An Approach to Anytime Learning
Abstract
Anytime learning is a general approach to continuous learning in a changing environment. The agent's learning module continuously tests new strategies against a simulation model of the task environment, and dynamically updates the knowledge base used by the agent on the basis of the results. The execution module controls the agent's interaction with the environment, and includes a monitor that can dynamically modify the simulation model based on its observations of the environment. When the simulation model is modified, the learning process is restarted on the modified model. The learning system is assumed to operate indefinitely, and the execution system uses the results of learning as they become available. An experimental study tests one of the key aspects of this design using a two-agent cat-and-mouse game as the task environment.
Cite
Text
Grefenstette and Ramsey. "An Approach to Anytime Learning." International Conference on Machine Learning, 1992. doi:10.1016/B978-1-55860-247-2.50029-2Markdown
[Grefenstette and Ramsey. "An Approach to Anytime Learning." International Conference on Machine Learning, 1992.](https://mlanthology.org/icml/1992/grefenstette1992icml-approach/) doi:10.1016/B978-1-55860-247-2.50029-2BibTeX
@inproceedings{grefenstette1992icml-approach,
title = {{An Approach to Anytime Learning}},
author = {Grefenstette, John J. and Ramsey, Connie Loggia},
booktitle = {International Conference on Machine Learning},
year = {1992},
pages = {189-195},
doi = {10.1016/B978-1-55860-247-2.50029-2},
url = {https://mlanthology.org/icml/1992/grefenstette1992icml-approach/}
}