Optimal strategies in Markov decision processes with finitely additive evaluations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912942699577344 |
|---|---|
| author | Flesch, János Predtetchinski, Arkadi Sudderth, William D Venel, Xavier |
| author_facet | Flesch, János Predtetchinski, Arkadi Sudderth, William D Venel, Xavier |
| contents | We study infinite-horizon Markov decision processes (MDPs) where the decision maker evaluates each of her strategies by aggregating the infinite stream of expected stage-rewards. The crucial feature of our approach is that the aggregation is performed by means of a given diffuse charge (a diffuse finitely additive probability measure) on the set of stages. The results of Neyman [2023] imply that in this setting, in every MDP with finite state and action spaces, the decision maker has a pure optimal strategy as long as the diffuse charge satisfies the time value of money principle. His result raises the question of existence of an optimal strategy without additional assumptions on the aggregation charge. We answer this question in the negative with a counterexample. With a delicately constructed aggregation charge, the MDP has no optimal strategy at all, neither pure nor randomized. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_04226 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Optimal strategies in Markov decision processes with finitely additive evaluations Flesch, János Predtetchinski, Arkadi Sudderth, William D Venel, Xavier Optimization and Control Theoretical Economics 90C40, 28A60 We study infinite-horizon Markov decision processes (MDPs) where the decision maker evaluates each of her strategies by aggregating the infinite stream of expected stage-rewards. The crucial feature of our approach is that the aggregation is performed by means of a given diffuse charge (a diffuse finitely additive probability measure) on the set of stages. The results of Neyman [2023] imply that in this setting, in every MDP with finite state and action spaces, the decision maker has a pure optimal strategy as long as the diffuse charge satisfies the time value of money principle. His result raises the question of existence of an optimal strategy without additional assumptions on the aggregation charge. We answer this question in the negative with a counterexample. With a delicately constructed aggregation charge, the MDP has no optimal strategy at all, neither pure nor randomized. |
| title | Optimal strategies in Markov decision processes with finitely additive evaluations |
| topic | Optimization and Control Theoretical Economics 90C40, 28A60 |
| url | https://arxiv.org/abs/2603.04226 |