Comparing Action-Query Strategies in Semi-Autonomous Agents
Abstract
We consider settings in which a semi-autonomous agent has uncertain knowledge about its environment, but can ask what action the human operator would prefer taking in the current or in a potential future state. Asking queries can improve behavior, but if queries come at a cost (e.g., due to limited operator attention), the value of each query should be maximized. We compare two strategies for selecting action queries: 1) based on myopically maximizing expected gain in long-term value, and 2) based on myopically minimizing uncertainty in the agent's policy representation. We show empirically that the first strategy tends to select more valuable queries, and that a hybrid method can outperform either method alone in settings with limited computation.
Cite
Text
Cohn et al. "Comparing Action-Query Strategies in Semi-Autonomous Agents." AAAI Conference on Artificial Intelligence, 2011. doi:10.1609/AAAI.V25I1.7992Markdown
[Cohn et al. "Comparing Action-Query Strategies in Semi-Autonomous Agents." AAAI Conference on Artificial Intelligence, 2011.](https://mlanthology.org/aaai/2011/cohn2011aaai-comparing/) doi:10.1609/AAAI.V25I1.7992BibTeX
@inproceedings{cohn2011aaai-comparing,
title = {{Comparing Action-Query Strategies in Semi-Autonomous Agents}},
author = {Cohn, Robert and Durfee, Edmund H. and Singh, Satinder},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2011},
pages = {1102-1107},
doi = {10.1609/AAAI.V25I1.7992},
url = {https://mlanthology.org/aaai/2011/cohn2011aaai-comparing/}
}