Asymptotic Lipschitz regularity for tug-of-war games with varying probabilities
\'Angel Arroyo, Hannes Luiro, Mikko Parviainen, Eero Ruosteenoja

TL;DR
This paper establishes an asymptotic Lipschitz regularity result for the value functions of tug-of-war games with variable probabilities, using a novel game-theoretic coupling approach.
Contribution
It introduces a new method to prove Lipschitz regularity for variable-probability tug-of-war games through a coupling-based analysis.
Findings
Proves asymptotic Lipschitz regularity of value functions.
Develops a game-theoretic coupling technique for analysis.
Extends regularity results to games with varying probabilities.
Abstract
We prove an asymptotic Lipschitz estimate for value functions of tug-of-war games with varying probabilities defined in . The method of the proof is based on a game-theoretic idea to estimate the value of a related game defined in via couplings.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
