Constant Payoff Property in Zero-Sum Stochastic Games with a Finite Horizon
Thomas Ragel, Bruno Ziliotto

TL;DR
This paper proves that in long finite zero-sum stochastic games, players can adopt strategies ensuring the average payoff remains close to the game's value throughout, extending the constant payoff property beyond previously known game types.
Contribution
It establishes the constant payoff property for finite zero-sum stochastic games with sufficiently long durations, generalizing prior results.
Findings
Existence of approximately optimal strategies with constant payoff property
The property holds for sufficiently long game durations
Extends the constant payoff property beyond absorbing and discounted games
Abstract
This paper examines finite zero-sum stochastic games and demonstrates that when the game's duration is sufficiently long, there exists a pair of approximately optimal strategies such that the expected average payoff at any point in the game remains close to the value. This property, known as the \textit{constant payoff property}, was previously established only for absorbing games and discounted stochastic games.
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.
Taxonomy
TopicsEconomic theories and models · Game Theory and Applications · Game Theory and Voting Systems
