A Cantor-Kantorovich Metric Between Markov Decision Processes with Application to Transfer Learning

Adrien Banse, Venkatraman Renganathan, Raphaël M. Jungers
7/11/2024
cs.LGcs.AI

No confident code implementation found for this paper. 2 possible matches can be shown below.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 2 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Comparing Labeled Markov Chains: A Cantor-Kantorovich Approach

86% match2025

A Kernel Perspective on Behavioural Metrics for Markov Decision Processes

85% match2023

Learning The Minimum Action Distance

83% match2025

Reinforcement Learning in the Wild with Maximum Likelihood-based Model Transfer

81% match2023

Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making

80% match1 repo302024

An MRP Formulation for Supervised Learning: Generalized Temporal Difference Learning Models

80% match2024

Cite this paper

@article{banse2024cantorkantorovich,
  title  = {A Cantor-Kantorovich Metric Between Markov Decision Processes with Application to Transfer Learning},
  author = {Adrien Banse and Venkatraman Renganathan and Raphaël M. Jungers},
  year   = {2024},
  eprint = {2407.08324},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2407.08324v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2407.08324.svg)](https://codeofpaper.com/paper/2407.08324)

Discussion