A Cantor-Kantorovich Metric Between Markov Decision Processes with Application to Transfer Learning
Machine Learning
2024-07-12 v1 Artificial Intelligence
Abstract
We extend the notion of Cantor-Kantorovich distance between Markov chains introduced by (Banse et al., 2023) in the context of Markov Decision Processes (MDPs). The proposed metric is well-defined and can be efficiently approximated given a finite horizon. Then, we provide numerical evidences that the latter metric can lead to interesting applications in the field of reinforcement learning. In particular, we show that it could be used for forecasting the performance of transfer learning algorithms.
Cite
@article{arxiv.2407.08324,
title = {A Cantor-Kantorovich Metric Between Markov Decision Processes with Application to Transfer Learning},
author = {Adrien Banse and Venkatraman Renganathan and Raphaël M. Jungers},
journal= {arXiv preprint arXiv:2407.08324},
year = {2024}
}
Comments
Presented at the 26th International Symposium on Mathematical Theory of Networks and Systems (Cambridge, UK)