Hedged Learning: Regret-Minimization with Learning Experts
Abstract
In non-cooperative multi-agent situations, there cannot exist a globally optimal, yet opponent-independent learning algorithm. Regret-minimization over a set of strategies optimized for potential opponent models is proposed as a good framework for deciding how to behave in such situations. Using longer playing horizons and experts that learn as they play, the regret-minimization framework can be extended to overcome several shortcomings of earlier approaches to the problem of multi-agent learning.
Cite
Text
Chang and Kaelbling. "Hedged Learning: Regret-Minimization with Learning Experts." International Conference on Machine Learning, 2005. doi:10.1145/1102351.1102367Markdown
[Chang and Kaelbling. "Hedged Learning: Regret-Minimization with Learning Experts." International Conference on Machine Learning, 2005.](https://mlanthology.org/icml/2005/chang2005icml-hedged/) doi:10.1145/1102351.1102367BibTeX
@inproceedings{chang2005icml-hedged,
title = {{Hedged Learning: Regret-Minimization with Learning Experts}},
author = {Chang, Yu-Han and Kaelbling, Leslie Pack},
booktitle = {International Conference on Machine Learning},
year = {2005},
pages = {121-128},
doi = {10.1145/1102351.1102367},
url = {https://mlanthology.org/icml/2005/chang2005icml-hedged/}
}