Adaptive Cognitive Orthotics: Combining Reinforcement Learning and Constraint-Based Temporal Reasoning
Abstract
Reminder systems support people with impaired prospective memory and/or executive function, by providing them with reminders of their functional daily activities. We integrate temporal constraint reasoning withreinforcement learning (RL) to build an adaptive reminder system and in asimulated environment demonstrate that it can personalize to a user and adaptto both short- and long-term changes. In addition to advancing the applicationdomain, our integrated algorithm contributes to research on temporal constraint reasoning by showing how RL can select an optimal policy from amongst a set of temporally consistent ones, and it contributes to the work on RL by showing how temporal constraint reasoning can be used to dramatically reduce the space of actions from which an RL agent needs to learn.
Cite
Text
Rudary et al. "Adaptive Cognitive Orthotics: Combining Reinforcement Learning and Constraint-Based Temporal Reasoning." International Conference on Machine Learning, 2004. doi:10.1145/1015330.1015411Markdown
[Rudary et al. "Adaptive Cognitive Orthotics: Combining Reinforcement Learning and Constraint-Based Temporal Reasoning." International Conference on Machine Learning, 2004.](https://mlanthology.org/icml/2004/rudary2004icml-adaptive/) doi:10.1145/1015330.1015411BibTeX
@inproceedings{rudary2004icml-adaptive,
title = {{Adaptive Cognitive Orthotics: Combining Reinforcement Learning and Constraint-Based Temporal Reasoning}},
author = {Rudary, Matthew R. and Singh, Satinder and Pollack, Martha E.},
booktitle = {International Conference on Machine Learning},
year = {2004},
doi = {10.1145/1015330.1015411},
url = {https://mlanthology.org/icml/2004/rudary2004icml-adaptive/}
}