Blackwell-Optimal Strategies in Priority Mean-Payoff Games
Hugo Gimbert (LaBRI), Wies{\l}aw Zielonka (Liafa)

TL;DR
This paper establishes a connection between discounted and priority mean-payoff games by showing that strategies optimal for near-1 discount factors are also optimal for priority mean-payoff games, unifying these game classes.
Contribution
It demonstrates that deterministic memoryless strategies optimal in discounted games with high discount factors are also optimal in priority mean-payoff games, revealing a strong theoretical link.
Findings
Optimal strategies for discounted games extend to priority mean-payoff games.
A strong link between discounted and priority mean-payoff games is established.
The results unify two important classes of stochastic games.
Abstract
We examine perfect information stochastic mean-payoff games - a class of games containing as special sub-classes the usual mean-payoff games and parity games. We show that deterministic memoryless strategies that are optimal for discounted games with state-dependent discount factors close to 1 are optimal for priority mean-payoff games establishing a strong link between these two classes.
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.
