Performance Guarantees for Homomorphisms Beyond Markov Decision Processes
Abstract
Most real-world problems have huge state and/or action spaces. Therefore, a naive application of existing tabular solution methods is not tractable on such problems. Nonetheless, these solution methods are quite useful if an agent has access to a relatively small state-action space homomorphism of the true environment and near-optimal performance is guaranteed by the map. A plethora of research is focused on the case when the homomorphism is a Markovian representation of the underlying process. However, we show that nearoptimal performance is sometimes guaranteed even if the homomorphism is non-Markovian.
Cite
Text
Majeed and Hutter. "Performance Guarantees for Homomorphisms Beyond Markov Decision Processes." AAAI Conference on Artificial Intelligence, 2019. doi:10.1609/AAAI.V33I01.33017659Markdown
[Majeed and Hutter. "Performance Guarantees for Homomorphisms Beyond Markov Decision Processes." AAAI Conference on Artificial Intelligence, 2019.](https://mlanthology.org/aaai/2019/majeed2019aaai-performance/) doi:10.1609/AAAI.V33I01.33017659BibTeX
@inproceedings{majeed2019aaai-performance,
title = {{Performance Guarantees for Homomorphisms Beyond Markov Decision Processes}},
author = {Majeed, Sultan Javed and Hutter, Marcus},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2019},
pages = {7659-7666},
doi = {10.1609/AAAI.V33I01.33017659},
url = {https://mlanthology.org/aaai/2019/majeed2019aaai-performance/}
}