Optimising expectation with guarantees for window mean payoff in Markov decision processes
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909452898140160 |
|---|---|
| author | Gaba, Pranshu Guha, Shibashis |
| author_facet | Gaba, Pranshu Guha, Shibashis |
| contents | The window mean-payoff objective strengthens the classical mean-payoff objective by computing the mean-payoff over a finite window that slides along an infinite path. Two variants have been considered: in one variant, the maximum window length is fixed and given, while in the other, it is not fixed but is required to be bounded. In this paper, we look at the problem of synthesising strategies in Markov decision processes that maximise the window mean-payoff value in expectation, while also simultaneously guaranteeing that the value is above a certain threshold. We solve the synthesis problem for three different kinds of guarantees: sure (that needs to be satisfied in the worst-case, that is, for an adversarial environment), almost-sure (that needs to be satisfied with probability one), and probabilistic (that needs to be satisfied with at least some given probability $p$).
We show that for fixed window mean-payoff objective, all the three problems are in $\mathsf{PTIME}$, while for bounded window mean-payoff objective, they are in $\mathsf{NP} \cap \mathsf{coNP}$, and thus have the same complexity as for maximising the expected performance without any guarantee. Moreover, we show that pure finite-memory strategies suffice for maximising the expectation with sure and almost-sure guarantees, whereas, for maximising expectation with a probabilistic guarantee, randomised strategies are necessary in general. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_05384 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Optimising expectation with guarantees for window mean payoff in Markov decision processes Gaba, Pranshu Guha, Shibashis Computer Science and Game Theory The window mean-payoff objective strengthens the classical mean-payoff objective by computing the mean-payoff over a finite window that slides along an infinite path. Two variants have been considered: in one variant, the maximum window length is fixed and given, while in the other, it is not fixed but is required to be bounded. In this paper, we look at the problem of synthesising strategies in Markov decision processes that maximise the window mean-payoff value in expectation, while also simultaneously guaranteeing that the value is above a certain threshold. We solve the synthesis problem for three different kinds of guarantees: sure (that needs to be satisfied in the worst-case, that is, for an adversarial environment), almost-sure (that needs to be satisfied with probability one), and probabilistic (that needs to be satisfied with at least some given probability $p$). We show that for fixed window mean-payoff objective, all the three problems are in $\mathsf{PTIME}$, while for bounded window mean-payoff objective, they are in $\mathsf{NP} \cap \mathsf{coNP}$, and thus have the same complexity as for maximising the expected performance without any guarantee. Moreover, we show that pure finite-memory strategies suffice for maximising the expectation with sure and almost-sure guarantees, whereas, for maximising expectation with a probabilistic guarantee, randomised strategies are necessary in general. |
| title | Optimising expectation with guarantees for window mean payoff in Markov decision processes |
| topic | Computer Science and Game Theory |
| url | https://arxiv.org/abs/2501.05384 |